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

    Neuronpedia

    INDEX
    Explanations

    on

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     κρα
    -0.07
     blackColor
    -0.07
     양
    -0.07
    jící
    -0.06
     inflicted
    -0.06
     prisons
    -0.06
    /renderer
    -0.06
     anticipating
    -0.06
    ΟΛ
    -0.06
     obedience
    -0.06
    POSITIVE LOGITS
    WATCH
    0.07
    EUR
    0.06
    0.06
     自
    0.06
    ']):
    0.06
    _BODY
    0.06
    castle
    0.06
     만족
    0.06
    uder
    0.06
    emet
    0.06
    Act Density 0.063%

    No Known Activations