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

    Neuronpedia

    INDEX
    Explanations

    General advice/commentary

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _panel
    -0.07
     контроль
    -0.07
    таки
    -0.06
    _male
    -0.06
    tok
    -0.06
    cue
    -0.06
    may
    -0.06
    TAIL
    -0.06
     may
    -0.06
     sofort
    -0.06
    POSITIVE LOGITS
     styles
    0.07
    imag
    0.07
    (quantity
    0.06
    /comment
    0.06
    ्क
    0.06
    /?
    0.06
    752
    0.06
    break
    0.06
    .IntegerField
    0.06
     /↵
    0.06
    Act Density 0.022%

    No Known Activations