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

    Neuronpedia

    INDEX
    Explanations

    For

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     light
    -0.08
     wide
    -0.07
     Ấ
    -0.07
     enquanto
    -0.07
    insic
    -0.07
    ительные
    -0.07
     CLOCK
    -0.07
     penny
    -0.07
     mesa
    -0.06
     Innovative
    -0.06
    POSITIVE LOGITS
     For
    0.08
    For
    0.07
    ():
↵
    0.06
    /');↵
    0.06
    decess
    0.06
    .For
    0.06
    (Box
    0.06
     cancelled
    0.06
     Kad
    0.06
    (patient
    0.06
    Act Density 0.023%

    No Known Activations