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

    Neuronpedia

    INDEX
    Explanations

    sulfides and resistivity

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     for
    0.88
    ā
    0.78
    is
    0.75
    ↵
    0.73
     by
    0.71
    at
    0.70
     For
    0.70
    for
    0.68
    ە
    0.67
    ंनो
    0.66
    POSITIVE LOGITS
    u
    0.91
    แต่
    0.83
    AL
    0.81
    та
    0.79
     način
    0.77
    apayati
    0.76
     لكن
    0.75
     реша
    0.75
    И
    0.73
     denominada
    0.72
    Act Density 0.002%

    No Known Activations