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

    Neuronpedia

    INDEX
    Explanations

    references to specific technical terms and abbreviations related to a particular framework or technical setting

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

    HT

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     BEC
    -0.50
     betweenstory
    -0.45
     Meksiku
    -0.44
     Autorisations
    -0.44
     Klaus
    -0.44
    BAG
    -0.43
    DebuggerStep
    -0.43
    ãng
    -0.43
     صوتيه
    -0.43
    NewReader
    -0.42
    POSITIVE LOGITS
     HT
    2.08
    HT
    1.78
     ht
    1.27
     Ht
    1.19
    Ht
    1.05
    HTC
    0.90
    ht
    0.85
     HTC
    0.85
     HTS
    0.81
     HTT
    0.80
    Act Density 0.015%

    No Known Activations