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

    Neuronpedia

    INDEX
    Explanations

    proper nouns and specific programming terms

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

    Gnocchi software and code snippets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    majánló
    -0.61
    IBOutlet
    -0.60
    HostException
    -0.58
    튿
    -0.58
    遠い
    -0.57
    thinkable
    -0.56
    TargetApi
    -0.56
    unculus
    -0.54
    ISupport
    -0.54
    ukung
    -0.54
    POSITIVE LOGITS
     Malibu
    1.03
    lorette
    0.55
    pix
    0.40
    Mali
    0.38
     pix
    0.36
     跳转至
    0.36
    delwed
    0.35
    Neymar
    0.34
     Neymar
    0.34
    PyExc
    0.34
    Act Density 0.002%

    No Known Activations