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

    Neuronpedia

    INDEX
    Explanations

    violence

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ze
    -0.07
     Scope
    -0.06
    城市
    -0.06
    fait
    -0.06
    oco
    -0.06
    imento
    -0.06
    iller
    -0.06
     qual
    -0.06
    rams
    -0.06
     weights
    -0.06
    POSITIVE LOGITS
     -=
    0.08
     contempt
    0.06
    complexContent
    0.06
     علمی
    0.06
     relação
    0.06
    Sep
    0.06
     intertwined
    0.06
    (JNIEnv
    0.06
     UIResponder
    0.06
     nä
    0.06
    Act Density 0.037%

    No Known Activations