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

    Neuronpedia

    INDEX
    Explanations

    datetime module usage

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    are
    0.48
    ridge
    0.45
     другу
    0.45
    更
    0.44
    addie
    0.44
    linson
    0.44
    erm
    0.44
    reten
    0.44
    rich
    0.43
    ressant
    0.43
    POSITIVE LOGITS
     prikaz
    0.45
     gird
    0.44
     juta
    0.43
    ذی
    0.43
     cabe
    0.43
     cilt
    0.43
    割り
    0.42
     suffit
    0.41
    系の
    0.41
     bygone
    0.40
    Act Density 0.002%

    No Known Activations