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

    Neuronpedia

    INDEX
    Explanations

    new systems or features

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    MathML
    0.80
     precisam
    0.80
     Customize
    0.77
     pudieran
    0.76
     siquiera
    0.75
    Customize
    0.75
    encial
    0.74
    ोस
    0.74
    ADH
    0.73
    ম্ম
    0.73
    POSITIVE LOGITS
    )");
    0.79
     ข้อ
    0.77
    ྫ
    0.76
     énergétique
    0.75
    erche
    0.74
    錘
    0.73
    ეხ
    0.71
    ecek
    0.70
    نګ
    0.69
    ெட்
    0.68
    Act Density 0.001%

    No Known Activations