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

    Neuronpedia

    INDEX
    Explanations

    print statements, formatting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    infodisc
    0.45
    黑暗
    0.44
     उपरोक्त
    0.43
    很是
    0.42
    讒
    0.42
    Aryan
    0.41
     necessariamente
    0.40
    同様
    0.40
    色素
    0.40
    ligare
    0.39
    POSITIVE LOGITS
     where
    0.52
    |
    0.50
    ",
    0.47
     MS
    0.46
    ",(
    0.46
     when
    0.46
     which
    0.46
     [
    0.46
    NZ
    0.45
    ↵
    0.45
    Act Density 0.023%

    No Known Activations