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

    Neuronpedia

    INDEX
    Explanations

    text following certain tokens

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ournal
    0.86
    > </
    0.72
    ian
    0.71
     sesu
    0.70
    ovalo
    0.69
    োন
    0.69
    orange
    0.69
    ograd
    0.68
    illos
    0.66
     französ
    0.66
    POSITIVE LOGITS
    م
    1.21
    ER
    0.84
     augmenter
    0.84
    ेशनल
    0.83
    cito
    0.80
     leukocytes
    0.80
     synthesizing
    0.80
     брать
    0.79
    ر
    0.79
    ει
    0.79
    Act Density 0.001%

    No Known Activations