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

    Neuronpedia

    INDEX
    Explanations

    mathematical formulas and accounts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     anastomosis
    0.56
    ização
    0.53
    。</
    0.52
    बिहार
    0.52
    Π
    0.52
     médiane
    0.51
    对抗
    0.50
     диамет
    0.50
     supplémentaires
    0.49
     offizi
    0.49
    POSITIVE LOGITS
    ())
    0.52
    lar
    0.49
    oya
    0.49
    aml
    0.49
     관계로
    0.48
    f
    0.47
    able
    0.47
    amo
    0.46
    '})
    0.46
    arlene
    0.46
    Act Density 0.000%

    No Known Activations