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

    Neuronpedia

    INDEX
    Explanations

    hypothetical situations and changes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    และ
    0.54
    ש
    0.52
    드
    0.50
     અને
    0.50
    לת
    0.48
    及
    0.47
     ಮತ್ತು
    0.47
    व
    0.47
    בי
    0.46
    ची
    0.46
    POSITIVE LOGITS
     postulated
    0.44
     Ki
    0.42
     gleichen
    0.41
     الذين
    0.41
     cuyos
    0.41
     ki
    0.41
     Ni
    0.41
     mysteriously
    0.40
     whose
    0.40
     changed
    0.39
    Act Density 0.030%

    No Known Activations