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

    Neuronpedia

    INDEX
    Explanations

    numbers and carbon emissions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    錡
    0.41
     چاہئے
    0.38
     garantire
    0.38
     centering
    0.37
    Arts
    0.37
    ツール
    0.37
    ِّف
    0.37
    を作
    0.36
     worksheet
    0.36
    HARD
    0.36
    POSITIVE LOGITS
    veli
    0.42
    㡺
    0.36
    eton
    0.35
    radius
    0.35
    ional
    0.34
    ByIndex
    0.34
     Anzeigen
    0.33
    涜
    0.33
    kost
    0.33
    thol
    0.33
    Act Density 0.010%

    No Known Activations