Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    technical terms and functionalities related to data processing and serialization in programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Operations concerning decrypting, thawing, unzipping or unpacking

    np_acts-logits-general · gemini-2.0-flash

    unwrapping, unlocking, or decoding

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     саны
    -0.50
    Eksterne
    -0.49
     closure
    -0.47
    URLEncoder
    -0.47
    closed
    -0.47
     shuts
    -0.46
     Zä
    -0.46
    persist
    -0.45
     shutting
    -0.44
    Closed
    -0.44
    POSITIVE LOGITS
     unwra
    1.03
     thawed
    1.01
     unlocking
    1.01
     thawing
    0.98
     unlock
    0.96
     decoding
    0.93
     unblock
    0.93
     decode
    0.93
     unzip
    0.92
     unpacking
    0.92
    Act Density 0.395%

    No Known Activations