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

    Neuronpedia

    INDEX
    Explanations

    function

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     özgür
    -0.07
     tong
    -0.07
    .Progress
    -0.06
    allery
    -0.06
     arsen
    -0.06
    _Dep
    -0.06
    scanf
    -0.06
    कर
    -0.06
    	location
    -0.06
    .flow
    -0.06
    POSITIVE LOGITS
    <?=
    0.07
    ें↵
    0.07
    .MIN
    0.06
     Δη
    0.06
     baise
    0.06
     پي
    0.06
     overshadow
    0.06
     değişiklik
    0.06
    。↵
    0.06
    hetics
    0.06
    Act Density 0.024%

    No Known Activations