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

    Neuronpedia

    INDEX
    Explanations

    3 1 sequences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     perfeita
    0.85
     इंटेलिज
    0.79
    聰
    0.77
     Criteria
    0.77
    聪明
    0.77
    ociaż
    0.75
     pursue
    0.74
    ChatGPT
    0.74
     进行
    0.73
    ClassLoader
    0.73
    POSITIVE LOGITS
     eps
    0.86
     EPS
    0.80
    EPS
    0.71
     pò
    0.70
     es
    0.69
     p
    0.69
     levels
    0.67
     إ
    0.65
     defied
    0.65
    fass
    0.64
    Act Density 0.002%

    No Known Activations