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

    Neuronpedia

    INDEX
    Explanations

    AGR

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     posto
    -0.06
     bushes
    -0.06
    .fast
    -0.06
     brushes
    -0.06
     billionaires
    -0.06
     orn
    -0.06
    Clock
    -0.06
    _Line
    -0.06
     prol
    -0.06
    /rs
    -0.06
    POSITIVE LOGITS
    _PROXY
    0.07
     �
    0.07
     attached
    0.07
    BJ
    0.06
     Мор
    0.06
    .presentation
    0.06
    rates
    0.06
    ρα
    0.06
    を使
    0.06
    yi
    0.06
    Act Density 0.007%

    No Known Activations