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

    Neuronpedia

    INDEX
    Explanations

    work hours

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     doctors
    -0.07
    …but
    -0.07
     complexes
    -0.07
     Delaware
    -0.07
    -abortion
    -0.07
     gost
    -0.07
     are
    -0.07
    immers
    -0.06
    (土
    -0.06
    felt
    -0.06
    POSITIVE LOGITS
    іп
    0.07
    INA
    0.06
    сок
    0.06
    friend
    0.06
    flutter
    0.06
    HttpResponse
    0.06
     EventHandler
    0.05
     dorsal
    0.05
    _DESCRIPTION
    0.05
    次
    0.05
    Act Density 0.003%

    No Known Activations