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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _mon
    -0.07
    >&
    -0.06
     �
    -0.06
    30
    -0.06
     PRINT
    -0.06
    ویش
    -0.06
    44
    -0.06
    .On
    -0.06
     Johnston
    -0.06
    rical
    -0.06
    POSITIVE LOGITS
    ดำ
    0.07
    а
    0.07
    е
    0.07
    案
    0.07
    =__
    0.06
    c
    0.06
    u
    0.06
     паци
    0.06
    a
    0.06
    ает
    0.06
    Act Density 0.034%

    No Known Activations