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

    Neuronpedia

    INDEX
    Explanations

    alone or

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     domínio
    1.09
     saída
    0.99
     exerce
    0.97
     ausreichend
    0.96
     recebe
    0.93
     adequ
    0.91
     amarelo
    0.91
     incluem
    0.91
     isso
    0.90
    itarian
    0.89
    POSITIVE LOGITS
    м
    1.06
    я
    0.95
    л
    0.93
    но
    0.90
    у
    0.87
    р
    0.80
    ль
    0.80
    L
    0.78
    m
    0.73
    лист
    0.71
    Act Density 0.000%

    No Known Activations