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

    Neuronpedia

    INDEX
    Explanations

    Cons

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    KP
    -0.07
     couldn
    -0.07
     demi
    -0.07
     saber
    -0.06
    RU
    -0.06
     üzerine
    -0.06
     potvr
    -0.06
     SJ
    -0.06
    双
    -0.06
    ?).
    -0.06
    POSITIVE LOGITS
    ISMATCH
    0.07
    MemoryWarning
    0.07
    AINER
    0.06
     Imag
    0.06
    _CONST
    0.06
    //"
    0.06
     assumes
    0.06
    ामग
    0.06
     Kann
    0.06
    riteria
    0.06
    Act Density 0.702%

    No Known Activations