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

    Neuronpedia

    INDEX
    Explanations

    come with particles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ﻱ
    0.61
    Beg
    0.60
    同一
    0.59
    使其
    0.57
    Mol
    0.56
    럏
    0.56
     मार्गों
    0.56
    𝘢
    0.55
    Prevent
    0.54
    ത്തിനും
    0.54
    POSITIVE LOGITS
     down
    1.29
     up
    1.09
     out
    1.05
     forth
    0.96
     off
    0.79
    down
    0.73
     into
    0.71
     Down
    0.69
    ダウン
    0.68
     downs
    0.67
    Act Density 0.177%

    No Known Activations