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

    Neuronpedia

    INDEX
    Explanations

    code structure delimiters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    σμ
    0.42
    ᴸ
    0.42
     wax
    0.40
     laser
    0.39
     χ
    0.39
     জাম
    0.39
     સી
    0.38
     consentimiento
    0.38
     plano
    0.38
     מו
    0.38
    POSITIVE LOGITS
    İlk
    0.38
    zzet
    0.37
    гона
    0.37
    ulière
    0.36
     parserOptions
    0.35
    itya
    0.35
     trouv
    0.35
    <0x0D>
    0.35
    ınıza
    0.35
     sinds
    0.34
    Act Density 0.027%

    No Known Activations