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

    Neuronpedia

    INDEX
    Explanations

    expressions of belief, opinion, and judgment in a given context

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

    expressing beliefs or opinions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     coefficients
    -0.45
    Demografía
    -0.42
     coefficient
    -0.42
     typelib
    -0.40
     mochilas
    -0.37
    様子
    -0.36
     useParams
    -0.36
    Obrázky
    -0.36
     intptr
    -0.35
    KommentareTeilen
    -0.35
    POSITIVE LOGITS
    AutoScale
    0.49
    Aiheesta
    0.44
     שוליים
    0.44
    Vader
    0.43
     derog
    0.43
    ----</
    0.43
     SUPERIOR
    0.42
    setViewportView
    0.42
    ViewFeatures
    0.41
    stdc
    0.41
    Act Density 0.146%

    No Known Activations