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

    Neuronpedia

    INDEX
    Explanations

    spot price, instance, welds, or spotlight

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    us
    1.37
    ك
    1.08
    R
    0.94
    ς
    0.92
     by
    0.91
    Unsere
    0.89
     negligible
    0.88
    ),”
    0.88
    ח
    0.88
    SL
    0.87
    POSITIVE LOGITS
    spot
    1.21
    n
    1.17
    de
    1.15
    spots
    1.15
    。
    1.13
    大
    1.13
    ス
    1.10
     spot
    1.05
    ム
    1.05
    ，
    0.99
    Act Density 0.006%

    No Known Activations