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

    Neuronpedia

    INDEX
    Explanations

    capital, slower, deeper

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     עוד
    0.45
     कथित
    0.41
     hijos
    0.40
     craw
    0.39
    ято
    0.38
    于是
    0.38
    CEP
    0.38
     ERIC
    0.38
    ג
    0.38
     tengan
    0.38
    POSITIVE LOGITS
     Дэ
    0.43
     Retired
    0.37
     చేపట్ట
    0.37
     Wolfe
    0.36
     القيمه
    0.36
     slower
    0.36
    阪
    0.36
    mV
    0.36
     уйный
    0.35
     الزد
    0.35
    Act Density 0.002%

    No Known Activations