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

    Neuronpedia

    INDEX
    Explanations

    famous people and characters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    вани
    0.44
     excelled
    0.43
     Jako
    0.43
    ната
    0.43
     मेहनत
    0.42
    บน
    0.42
    お子
    0.42
     села
    0.41
    もあり
    0.41
     openers
    0.41
    POSITIVE LOGITS
    be
    0.52
    geist
    0.46
    us
    0.43
    ia
    0.40
    és
    0.40
    vät
    0.39
    م
    0.39
    cerpt
    0.38
    é
    0.38
    ende
    0.38
    Act Density 0.003%

    No Known Activations