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

    Neuronpedia

    INDEX
    Explanations

    technology and programming

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     adatt
    0.88
     R
    0.84
     н
    0.78
     Queries
    0.76
     пр
    0.72
     Р
    0.71
     A
    0.71
     র
    0.71
     ر
    0.70
     П
    0.69
    POSITIVE LOGITS
    S
    1.16
     S
    1.07
     Six
    0.86
     eighteen
    0.83
     eight
    0.81
    mashtami
    0.81
     Sosa
    0.81
    Six
    0.80
    ༧
    0.80
     Kwiatkowski
    0.79
    Act Density 0.000%

    No Known Activations