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

    Neuronpedia

    INDEX
    Explanations

    Comparisons

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ується
    -0.08
    영상
    -0.07
    entered
    -0.07
    hl
    -0.06
    _dll
    -0.06
    aggregate
    -0.06
    sealed
    -0.06
    alias
    -0.06
    SELF
    -0.06
    OMETRY
    -0.06
    POSITIVE LOGITS
    ={({
    0.06
     Ibrahim
    0.06
     humility
    0.06
     nhóm
    0.06
    .payment
    0.06
     関連
    0.06
     crazy
    0.06
    \Twig
    0.06
     prelim
    0.06
     Cologne
    0.06
    Act Density 0.423%

    No Known Activations