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

    Neuronpedia

    INDEX
    Explanations

    created by

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    結果
    0.48
    မည်
    0.45
    amard
    0.45
    Wes
    0.45
     امام
    0.43
     Hatt
    0.43
    Will
    0.43
    効果
    0.42
     Vlad
    0.42
    杪
    0.42
    POSITIVE LOGITS
     खराब
    0.46
     barr
    0.45
     Trench
    0.45
    มาย
    0.43
    纹
    0.43
     pompa
    0.43
     Newtonian
    0.42
    xious
    0.41
     divine
    0.41
    ки
    0.41
    Act Density 0.000%

    No Known Activations