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

    Neuronpedia

    INDEX
    Explanations

    return the result

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     জানে
    0.68
    認識
    0.67
    ס
    0.67
    p
    0.66
    getC
    0.65
    țul
    0.65
    的前提
    0.64
    計算
    0.63
     darah
    0.63
    ților
    0.63
    POSITIVE LOGITS
     ETFs
    0.82
    clusively
    0.82
    बर्ट
    0.79
     voluntad
    0.77
    ming
    0.75
    ಧ್ಯ
    0.75
    بانی
    0.75
    ব্যাক
    0.75
    brevi
    0.75
    artment
    0.74
    Act Density 0.000%

    No Known Activations