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

    Neuronpedia

    INDEX
    Explanations

    permits and requirements

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ны
    0.66
    нын
    0.63
    ಪಿ
    0.61
     ALP
    0.60
    Og
    0.58
     adal
    0.58
    治安
    0.57
    льны
    0.56
     zár
    0.55
     ताज
    0.54
    POSITIVE LOGITS
     Permits
    0.63
     📫
    0.59
     ☐
    0.58
     Proof
    0.57
     especie
    0.57
     lightness
    0.57
    ᆺ
    0.57
     permesso
    0.56
    🍆
    0.55
     енер
    0.55
    Act Density 0.000%

    No Known Activations