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

    Neuronpedia

    INDEX
    Explanations

    validation in code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     _,
    1.76
    頪
    1.73
    🅷
    1.72
    সাথে
    1.67
    itance
    1.62
    共
    1.59
    ersion
    1.59
     utterances
    1.58
    들이
    1.54
     utc
    1.52
    POSITIVE LOGITS
    ची
    1.47
    いい
    1.42
    el
    1.40
     mož
    1.39
    良い
    1.37
     pathetic
    1.36
    aduct
    1.36
     можа
    1.31
     Kopf
    1.29
    चा
    1.29
    Act Density 0.001%

    No Known Activations