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

    Neuronpedia

    INDEX
    Explanations

    code comments and descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ،
    0.77
     aneur
    0.56
     hinsichtlich
    0.53
     enjeux
    0.52
    ፣
    0.52
    ၊
    0.52
     چنین
    0.49
     crisi
    0.49
     przedsi
    0.49
    ؛
    0.47
    POSITIVE LOGITS
     TODO
    0.88
    TODO
    0.86
     For
    0.67
     This
    0.63
     Remove
    0.62
     Create
    0.61
     FIXME
    0.61
     Using
    0.61
     We
    0.58
     Use
    0.58
    Act Density 0.097%

    No Known Activations