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

    Neuronpedia

    INDEX
    Explanations

    noticing expect potentially

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     অত্যা
    0.44
     olika
    0.44
    তাকে
    0.43
    categ
    0.43
     резко
    0.42
    怆
    0.41
     plates
    0.41
     macam
    0.40
     amply
    0.40
    bagai
    0.39
    POSITIVE LOGITS
    Результа
    0.44
     причине
    0.41
    ერი
    0.39
    өрд
    0.39
    y
    0.39
    GK
    0.38
     रखने
    0.38
     നടത്തിയ
    0.37
    ंख्य
    0.37
    ียน
    0.37
    Act Density 0.001%

    No Known Activations