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

    Neuronpedia

    INDEX
    Explanations

    need

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    085
    -0.07
     bullish
    -0.06
     naked
    -0.06
    isAdmin
    -0.06
    <Date
    -0.06
    ioso
    -0.06
     Adobe
    -0.06
     blond
    -0.06
     Magnum
    -0.06
     virus
    -0.06
    POSITIVE LOGITS
    enties
    0.07
     بسیار
    0.07
     맥
    0.07
    くな
    0.07
    ğinden
    0.07
    yer
    0.07
     frac
    0.07
    ies
    0.06
    [state
    0.06
    죽
    0.06
    Act Density 0.117%

    No Known Activations