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

    Neuronpedia

    INDEX
    Explanations

    org imports

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ا
    1.15
    a
    1.05
    e
    0.98
    Florida
    0.97
     timescales
    0.93
     Zodiac
    0.91
     pihaknya
    0.90
    springframework
    0.90
     simultaneous
    0.90
    Twilight
    0.89
    POSITIVE LOGITS
    엇
    1.06
    க்
    1.05
    िवे
    1.02
    ség
    1.01
    ன்க
    1.01
     এছাড়া
    0.97
    னி
    0.96
    aren
    0.95
    ଛ
    0.94
    illos
    0.94
    Act Density 0.008%

    No Known Activations