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

    Neuronpedia

    INDEX
    Explanations

    method capacity

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    тири
    0.77
    s
    0.76
    ватися
    0.72
    trait
    0.70
     infix
    0.69
    ｃ
    0.69
    sax
    0.69
    ULTURE
    0.68
    CONTENTS
    0.68
    シス
    0.68
    POSITIVE LOGITS
     berätt
    0.73
     Noetherian
    0.73
     Před
    0.72
    க்கார
    0.68
    ুগত্য
    0.68
     pokrač
    0.67
     funcionários
    0.66
     hükü
    0.66
     kişiler
    0.66
     അഭ
    0.65
    Act Density 0.000%

    No Known Activations