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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    /comment
    -0.07
     damaging
    -0.06
    (stats
    -0.06
     public
    -0.06
     Yoga
    -0.06
    JB
    -0.06
    asz
    -0.06
    _VERBOSE
    -0.06
     psychologists
    -0.06
     Expect
    -0.06
    POSITIVE LOGITS
    MeasureSpec
    0.07
    elaide
    0.06
    *ft
    0.06
    ožná
    0.06
    محمد
    0.06
    tensor
    0.06
    latesAutoresizingMaskIntoConstraints
    0.06
    �
    0.06
    0.06
    Mounted
    0.06
    Act Density 0.008%

    No Known Activations