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

    Neuronpedia

    INDEX
    Explanations

    violence and conflict

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (Network
    -0.07
    Tasks
    -0.07
    quotelev
    -0.07
    ?option
    -0.06
     studied
    -0.06
     entertain
    -0.06
    _tc
    -0.06
    ويس
    -0.06
     //////////////////////////////////////////////////////////////////////////
    -0.06
    Comments
    -0.06
    POSITIVE LOGITS
     sag
    0.07
     colore
    0.07
     al
    0.07
     disgr
    0.06
    spr
    0.06
     действ
    0.06
     кур
    0.06
    ність
    0.06
     Reactive
    0.06
    hoe
    0.06
    Act Density 0.048%

    No Known Activations