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

    Neuronpedia

    INDEX
    Explanations

    IllegalArgument Exception

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ৩
    0.84
    3
    0.72
    ३
    0.71
    ب
    0.71
    Als
    0.68
    ৪
    0.66
    ۳
    0.65
    STATE
    0.62
    THERE
    0.61
    $+
    0.61
    POSITIVE LOGITS
    esh
    0.58
     xScale
    0.56
    esis
    0.48
     rash
    0.48
     την
    0.48
    ulse
    0.47
    etes
    0.47
     แม
    0.47
    벅
    0.47
    imet
    0.47
    Act Density 0.000%

    No Known Activations