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

    Neuronpedia

    INDEX
    Explanations

    technical jargon and function calls related to programming and debugging processes

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

    abbreviations and codes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    sendLogPayload
    -0.52
    MLLoader
    -0.48
     secret
    -0.48
    酸
    -0.46
    ه
    -0.46
     continent
    -0.46
    SequentialGroup
    -0.46
    specialchars
    -0.45
    הח
    -0.45
     ра
    -0.44
    POSITIVE LOGITS
     tgt
    0.57
     Atty
    0.56
    chk
    0.56
     Hrs
    0.54
     stmt
    0.54
    tgt
    0.53
    Rptr
    0.53
     fwd
    0.53
     lvl
    0.53
    Dlg
    0.53
    Act Density 0.056%

    No Known Activations