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

    Neuronpedia

    INDEX
    Explanations

    expressions of agreement or acknowledgment

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

    "OK" (or similar) followed by a comma

    np_acts-logits-general · gemini-2.0-flash

    acknowledgement or transition

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    twimg
    -0.67
    UTERS
    -0.58
    sidemargin
    -0.58
    bcryptjs
    -0.57
    amable
    -0.56
    NOSIS
    -0.56
    mappedBy
    -0.56
    BeginContext
    -0.56
    lessness
    -0.55
     跳转至
    -0.54
    POSITIVE LOGITS
    lahoma
    0.82
     fine
    0.64
     FINE
    0.62
    fine
    0.62
    alright
    0.62
    inawa
    0.61
    LAHOMA
    0.58
     boomer
    0.57
    SourceChecksum
    0.57
     OMITBAD
    0.57
    Act Density 0.040%

    No Known Activations