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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     mustard
    -0.08
     wire
    -0.07
    _continue
    -0.07
    Math
    -0.07
     Bomb
    -0.07
    ляли
    -0.06
    末
    -0.06
    ляє
    -0.06
    死亡
    -0.06
    _tot
    -0.06
    POSITIVE LOGITS
     FI
    0.07
    eterminate
    0.07
     dims
    0.07
     understanding
    0.06
    _ASSIGN
    0.06
    >Show
    0.06
    xiety
    0.06
    أس
    0.06
    ín
    0.06
    .readValue
    0.06
    Act Density 0.063%

    No Known Activations