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

    Neuronpedia

    INDEX
    Explanations

    as

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     função
    -0.08
     dangers
    -0.07
    iki
    -0.06
    Go
    -0.06
    Trade
    -0.06
     Abe
    -0.06
     kötü
    -0.06
     overcoming
    -0.06
    marked
    -0.06
     statuses
    -0.06
    POSITIVE LOGITS
    	sc
    0.06
     andra
    0.06
    unc
    0.06
     SPEED
    0.06
    iske
    0.06
    ReuseIdentifier
    0.06
     AudioClip
    0.06
     Поль
    0.06
    UNC
    0.06
    %p
    0.06
    Act Density 0.002%

    No Known Activations