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

    Neuronpedia

    INDEX
    Explanations

    collocations and grammatical structures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     common
    0.73
    시
    0.69
     average
    0.67
     process
    0.65
    re
    0.65
    ுங்கள்
    0.64
    BA
    0.64
    bad
    0.63
     rup
    0.63
     event
    0.63
    POSITIVE LOGITS
    នេះ
    0.91
     مہ
    0.85
     comprador
    0.85
    ႅ
    0.84
    їз
    0.84
     tonos
    0.83
    滃
    0.83
     تحقی
    0.82
     presentato
    0.82
    akkh
    0.82
    Act Density 0.000%

    No Known Activations