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

    Neuronpedia

    INDEX
    Explanations

    eagle and dolphins

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    د
    0.68
    ک
    0.61
    特徴
    0.54
    أة
    0.53
    م
    0.53
    ام
    0.52
     상품
    0.52
    وی
    0.51
    d
    0.51
    أ
    0.51
    POSITIVE LOGITS
    an
    0.54
     eagles
    0.46
     eagle
    0.46
    ,}
    0.45
    aching
    0.45
    ın
    0.44
     fija
    0.44
    re
    0.43
    ande
    0.43
    ̣c
    0.42
    Act Density 0.000%

    No Known Activations