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
     Unused
    -0.07
    ModelAttribute
    -0.06
     pisc
    -0.06
    ('#
    -0.06
    cas
    -0.06
     recuper
    -0.06
     ACCEPT
    -0.06
     بالا
    -0.06
    roperty
    -0.06
     تصو
    -0.05
    POSITIVE LOGITS
     charg
    0.07
     контролю
    0.07
     repairs
    0.07
    consum
    0.07
     định
    0.07
    MS
    0.07
    бина
    0.06
    LER
    0.06
    chef
    0.06
     고려
    0.06
    Act Density 0.000%

    No Known Activations