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

    Neuronpedia

    INDEX
    Explanations

    134

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     využí
    -0.07
    ælland
    -0.07
     plo
    -0.06
     Notification
    -0.06
     santa
    -0.06
    �
    -0.06
     Pointer
    -0.06
     zost
    -0.06
     lượt
    -0.06
    -ı
    -0.06
    POSITIVE LOGITS
    135
    0.09
    133
    0.09
    132
    0.08
    134
    0.08
     carc
    0.08
    akit
    0.07
     Parliament
    0.07
    amet
    0.07
     faults
    0.07
     Iron
    0.06
    Act Density 0.009%

    No Known Activations