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

    Neuronpedia

    INDEX
    Explanations

    numbers and symbols

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     incest
    0.50
     artículos
    0.50
     есте
    0.48
     neoliberal
    0.48
     epistem
    0.48
     आवश्यकताओं
    0.47
    ⁤
    0.47
     prinsip
    0.47
     hypertext
    0.46
     hablar
    0.46
    POSITIVE LOGITS
    %
    0.59
    0
    0.56
    +
    0.51
    L
    0.48
    0.48
    xff
    0.46
        
    0.43
    .
    0.42
    b
    0.41
    x
    0.41
    Act Density 0.505%

    No Known Activations