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

    Neuronpedia

    INDEX
    Explanations

    restoring

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     cesty
    -0.06
     Evil
    -0.06
     του
    -0.06
    upe
    -0.06
     svém
    -0.06
    τους
    -0.06
    .ProgressBar
    -0.06
     sik
    -0.06
    ated
    -0.06
    ät
    -0.06
    POSITIVE LOGITS
    .predict
    0.07
    هنگ
    0.06
    .pc
    0.06
     dependent
    0.06
    /GL
    0.06
     butcher
    0.06
     breaks
    0.06
     Banks
    0.06
     &&
    0.06
    373
    0.06
    Act Density 0.070%

    No Known Activations