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

    Neuronpedia

    INDEX
    Explanations

    words associated with social science papers

    oai_token-act-pair · gemini-2.0-flash

    to

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    WebVitals
    -0.82
    awtextra
    -0.73
     Monfieur
    -0.73
     كومونز
    -0.72
    :✨
    -0.69
     Efq
    -0.68
     Houſe
    -0.68
    omeness
    -0.68
     Jefus
    -0.68
     Reſ
    -0.67
    POSITIVE LOGITS
     to
    2.36
    to
    1.32
     To
    1.24
     TO
    1.13
    To
    1.06
    tobe
    0.82
    ToAdd
    0.79
    ToBe
    0.76
     να
    0.74
     לה
    0.73
    Act Density 4.449%

    No Known Activations