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

    Neuronpedia

    INDEX
    Explanations

    function argument definitions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Outer
    0.69
     Analog
    0.69
    OLI
    0.68
    থিত
    0.68
    amyl
    0.65
    WarningLevel
    0.64
    マリン
    0.64
    alti
    0.63
     adik
    0.63
     Parental
    0.63
    POSITIVE LOGITS
     derece
    0.65
    tour
    0.59
    鉉
    0.57
     উভ
    0.54
    usel
    0.53
    নো
    0.52
    ligen
    0.52
    viet
    0.52
     ব্যাপারে
    0.52
    JPN
    0.52
    Act Density 0.172%

    No Known Activations