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

    Neuronpedia

    INDEX
    Explanations

    code blocks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    hensive
    0.54
    licted
    0.52
    debt
    0.51
    weekly
    0.50
    Corruption
    0.48
    STTS
    0.48
    Leffler
    0.48
    Fols
    0.48
    GLASS
    0.48
    UNDS
    0.48
    POSITIVE LOGITS
     derive
    0.49
     CH
    0.49
     Ü
    0.47
     Chrome
    0.46
     Jak
    0.46
    ي
    0.45
     V
    0.45
     applied
    0.45
     symmetric
    0.45
     OUR
    0.44
    Act Density 0.002%

    No Known Activations