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

    Neuronpedia

    INDEX
    Explanations

    country songs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    л
    0.71
    ל
    0.71
    д
    0.69
    ف
    0.68
    ق
    0.64
    ك
    0.63
     atividade
    0.62
     gase
    0.62
    માં
    0.60
     aaya
    0.60
    POSITIVE LOGITS
    inen
    0.62
    em
    0.59
    ari
    0.59
    is
    0.58
    ixes
    0.57
    methylation
    0.57
    al
    0.57
    inders
    0.57
    ̀i
    0.57
    ir
    0.56
    Act Density 0.000%

    No Known Activations