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

    Neuronpedia

    INDEX
    Explanations

    division by zero or denominator

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     معناها
    0.38
     envie
    0.36
     जरूरतों
    0.36
     переви
    0.36
    整合
    0.36
     Crav
    0.35
     theseKeys
    0.34
     बगल
    0.34
     gewüns
    0.34
     unrel
    0.34
    POSITIVE LOGITS
     denominator
    2.13
     denominators
    1.90
    denominator
    1.86
     denominador
    1.72
    Denominator
    1.71
    denom
    1.47
     denomin
    1.46
     denom
    1.46
     denomination
    1.45
     denominations
    1.37
    Act Density 0.023%

    No Known Activations