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

    Neuronpedia

    INDEX
    Explanations

    bodily control and functions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     मजेदार
    0.49
    iversary
    0.48
    ری
    0.47
     scary
    0.47
    να
    0.47
    κε
    0.47
     Minggu
    0.46
    olation
    0.46
     την
    0.46
     গ্রেপ্তার
    0.45
    POSITIVE LOGITS
    க்ஸாண்ட
    0.46
    jd
    0.43
    toHaveBeen
    0.42
    ifie
    0.42
    MSE
    0.41
    ibase
    0.41
    ваш
    0.41
    ]^{
    0.40
    iteits
    0.39
    多种
    0.38
    Act Density 0.001%

    No Known Activations