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

    Neuronpedia

    INDEX
    Explanations

    comma

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .org
    -0.08
     '{
    -0.07
    новаж
    -0.06
     національ
    -0.06
    __$
    -0.06
     Banks
    -0.06
     channels
    -0.06
     winner
    -0.06
     안내
    -0.06
    bservice
    -0.06
    POSITIVE LOGITS
    DEF
    0.07
    .setFill
    0.07
    との
    0.07
     シ
    0.07
    ,it
    0.07
     etmesi
    0.07
     WARRANTIES
    0.06
    .sendStatus
    0.06
     pf
    0.06
    zew
    0.06
    Act Density 0.017%

    No Known Activations