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

    Neuronpedia

    INDEX
    Explanations

    technical terms

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    iranje
    0.59
    atten
    0.58
     اختصاص
    0.58
    atien
    0.58
    intosh
    0.57
    沣
    0.55
    onneur
    0.55
    狛
    0.55
    incent
    0.54
     Cate
    0.53
    POSITIVE LOGITS
     sav
    0.57
     unregulated
    0.55
    สอน
    0.54
     nevo
    0.54
     playas
    0.52
    бак
    0.52
    恸
    0.52
     unlucky
    0.51
     succeeded
    0.50
    ສົ
    0.50
    Act Density 0.000%

    No Known Activations