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

    Neuronpedia

    INDEX
    Explanations

    indicating an example or illustration

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    обу
    0.75
    Talk
    0.73
    es
    0.71
    ة
    0.70
     бан
    0.70
    madan
    0.69
    LOS
    0.69
     magna
    0.68
     الخ
    0.66
    typ
    0.65
    POSITIVE LOGITS
     example
    2.06
     instance
    1.91
    example
    1.65
    instance
    1.55
     ejemplo
    1.52
     مثال
    1.44
     exemple
    1.42
     eksempel
    1.39
     esempio
    1.36
     exemplo
    1.34
    Act Density 0.170%

    No Known Activations