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

    Neuronpedia

    INDEX
    Explanations

    author contexts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    讖
    0.52
    ক
    0.51
    ج
    0.50
    ו
    0.48
     Русский
    0.47
     Университе
    0.47
    ムー
    0.45
     художник
    0.45
    где
    0.45
    事実
    0.44
    POSITIVE LOGITS
     person
    0.52
    uffs
    0.51
     compiled
    0.49
    ully
    0.47
     autor
    0.47
    ade
    0.46
    ána
    0.46
     expertly
    0.46
     composed
    0.45
     as
    0.45
    Act Density 0.003%

    No Known Activations