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

    Neuronpedia

    INDEX
    Explanations

    expressions related to user names and identifiers

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

    full names and initials

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     snippetHide
    -0.73
     ligiloj
    -0.53
     newBuilder
    -0.52
     Taktlose
    -0.52
    pulumi
    -0.51
    ecap
    -0.50
    moveToFirst
    -0.49
    ValueStyle
    -0.49
    expandindo
    -0.49
    Derbyniad
    -0.47
    POSITIVE LOGITS
     fullName
    0.85
    FullName
    0.84
     fullname
    0.83
    fullname
    0.82
    fullName
    0.69
     name
    0.65
    姓名
    0.59
     NAME
    0.57
    name
    0.54
     navn
    0.54
    Act Density 0.002%

    No Known Activations