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

    Neuronpedia

    INDEX
    Explanations

    raised issues and questions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    oches
    0.83
    kün
    0.79
     క్ష
    0.76
     tapaht
    0.75
    ertz
    0.74
     thích
    0.73
    頹
    0.72
    ImageView
    0.72
    zeptember
    0.71
    챱
    0.71
    POSITIVE LOGITS
     raised
    3.05
     raise
    2.51
     raising
    2.44
     Raised
    2.42
    raised
    2.37
     raises
    2.30
    Raised
    2.28
     Raise
    2.17
    Raise
    2.13
    raise
    2.13
    Act Density 0.323%

    No Known Activations