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

    Neuronpedia

    INDEX
    Explanations

    life or death consequences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ப்போதும்
    0.50
    シ
    0.50
    こちら
    0.48
    Дан
    0.48
    では
    0.47
     aprobado
    0.47
    ර
    0.47
     организация
    0.46
     गोप
    0.45
    止
    0.45
    POSITIVE LOGITS
    indrome
    0.55
     +
    0.51
     durability
    0.51
     pregnancy
    0.50
     fake
    0.49
     pro
    0.49
     knight
    0.49
     exponents
    0.49
     life
    0.48
     metabolic
    0.48
    Act Density 0.012%

    No Known Activations