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

    Neuronpedia

    INDEX
    Explanations

    thyme and fatigue

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     It
    0.75
    这个
    0.57
     The
    0.55
    It
    0.54
    子的
    0.54
    ленных
    0.54
     Ā
    0.54
     An
    0.53
    IT
    0.53
    ﻤ
    0.53
    POSITIVE LOGITS
     եւ
    0.74
     һәм
    0.73
     және
    0.71
    ي
    0.68
    ؛
    0.65
    ווי
    0.64
     ۽
    0.63
    ،
    0.62
    }$
    0.61
     കോടതി
    0.59
    Act Density 0.011%

    No Known Activations