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

    Neuronpedia

    INDEX
    Explanations

    train

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    cedes
    -0.09
     به
    -0.08
     المطل
    -0.07
     Howell
    -0.07
    WAY
    -0.07
    كنولوجيا
    -0.07
     الأط
    -0.07
     یون
    -0.07
    াত্র
    -0.07
     upbeat
    -0.07
    POSITIVE LOGITS
     immunity
    0.09
    uf
    0.09
    �
    0.08
     oneself
    0.08
     soldiers
    0.08
     intellect
    0.08
     intentions
    0.08
     krv
    0.07
     eyesight
    0.07
     трен
    0.07
    Act Density 0.026%

    No Known Activations