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

    Neuronpedia

    INDEX
    Explanations

    academic texts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     On
    -0.07
     En
    -0.07
    In
    -0.07
     In
    -0.07
     via
    -0.06
     فی
    -0.06
     tonight
    -0.06
     na
    -0.06
     reservations
    -0.06
    statusCode
    -0.06
    POSITIVE LOGITS
     COMM
    0.07
    _dec
    0.07
    ्वप
    0.07
    láš
    0.06
    _det
    0.06
     kind
    0.06
    –
    0.06
    -An
    0.06
    Lit
    0.06
    _CHARS
    0.06
    Act Density 1.195%

    No Known Activations