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

    Neuronpedia

    INDEX
    Explanations

    Carlos Santana; Arrays.asList

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Radford
    0.41
    ایات
    0.41
     Angew
    0.39
    cusson
    0.38
    搁
    0.38
    sschutz
    0.38
    kec
    0.38
     Kyi
    0.37
     Fleurit
    0.37
    セイ
    0.37
    POSITIVE LOGITS
     singleton
    0.55
    singleton
    0.49
    binary
    0.45
     binary
    0.45
    Binary
    0.40
    synchronized
    0.40
    Singleton
    0.39
     ничего
    0.38
     Rot
    0.38
     Singleton
    0.36
    Act Density 0.002%

    No Known Activations