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

    Neuronpedia

    INDEX
    Explanations

    toxins

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     DRAW
    -0.10
    DRAW
    -0.08
    ATAR
    -0.08
     contest
    -0.08
    _Save
    -0.08
    قق
    -0.08
    omba
    -0.07
     Written
    -0.07
     भेट
    -0.07
    /save
    -0.07
    POSITIVE LOGITS
     alarms
    0.09
     globalization
    0.09
     bloodstream
    0.08
     systemic
    0.08
     skyrock
    0.08
     divergence
    0.08
     крови
    0.08
     Vigil
    0.08
    循环
    0.08
     ಬೆಳ
    0.08
    Act Density 0.004%

    No Known Activations