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

    Neuronpedia

    INDEX
    Explanations

    names

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    917
    -0.07
    _amt
    -0.07
     ух
    -0.07
    Plan
    -0.07
    868
    -0.06
     плен
    -0.06
     hale
    -0.06
     Tul
    -0.06
    .ctx
    -0.06
     суб
    -0.06
    POSITIVE LOGITS
    askets
    0.07
    TOKEN
    0.06
     hashing
    0.06
    rote
    0.06
    ={({
    0.06
    irection
    0.06
     cylinders
    0.06
    ']=
    0.06
    owner
    0.06
    ojení
    0.06
    Act Density 0.070%

    No Known Activations