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

    Neuronpedia

    INDEX
    Explanations

    ="

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Lair
    -0.08
    abbo
    -0.07
    ниця
    -0.06
    ÃO
    -0.06
    اوي
    -0.06
     {!
    -0.06
    ohan
    -0.06
    [`
    -0.06
    _brightness
    -0.06
     ΔΗΜ
    -0.06
    POSITIVE LOGITS
     denotes
    0.06
    tip
    0.06
    .An
    0.06
     Ví
    0.06
     Millions
    0.06
     motorcycles
    0.06
    logg
    0.06
    .Type
    0.06
    quiring
    0.06
     PWM
    0.06
    Act Density 0.001%

    No Known Activations