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

    Neuronpedia

    INDEX
    Explanations

    Code documentation

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    רצח
    -0.07
    慈
    -0.07
    WHO
    -0.07
    وت
    -0.07
    玎
    -0.07
    endet
    -0.07
    CGColor
    -0.07
    	strcat
    -0.07
    otr
    -0.07
    uvo
    -0.07
    POSITIVE LOGITS
    أسواق
    0.08
    河南省
    0.07
     saddle
    0.07
    building
    0.07
     STATIC
    0.07
    bottom
    0.07
    Holder
    0.07
     accur
    0.07
    Sq
    0.07
     Nº
    0.07
    Act Density 0.054%

    No Known Activations