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

    Neuronpedia

    INDEX
    Explanations

    by

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (iter
    -0.07
    .fade
    -0.06
     Torah
    -0.06
     heights
    -0.06
    .activate
    -0.06
    ná
    -0.06
    mere
    -0.06
     AppBar
    -0.06
    Column
    -0.06
    om
    -0.06
    POSITIVE LOGITS
     /**
    0.08
    /**
    0.08
     Sarah
    0.07
    .Selected
    0.06
    .contentSize
    0.06
     prag
    0.06
    Sleep
    0.06
    .h
    0.06
    опри
    0.06
     Honestly
    0.06
    Act Density 0.015%

    No Known Activations