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

    Neuronpedia

    INDEX
    Explanations

    verbs related to uploading or internet activity

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

    Verbs followed by adverbs or prepositions

    np_acts-logits-general · gemini-2.0-flash

    performing actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    +#+#
    -0.75
    Personendaten
    -0.70
    oneofs
    -0.69
    DoubleQuotes
    -0.67
    =$?
    -0.64
    contentLoaded
    -0.62
    sizeCache
    -0.62
    WriteBarrier
    -0.61
    دانشنامهٔ
    -0.60
    InstrumentedTest
    -0.59
    POSITIVE LOGITS
    mybatisplus
    0.74
     anything
    0.68
     them
    0.66
     anywhere
    0.64
     without
    0.64
     ulang
    0.62
     proprement
    0.61
    เอง
    0.58
    ########.
    0.57
    spesies
    0.57
    Act Density 0.846%

    No Known Activations