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

    Neuronpedia

    INDEX
    Explanations

    risk and metabolism

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     capaces
    0.41
     capaz
    0.38
     capazes
    0.38
    capable
    0.37
     capables
    0.37
     और
    0.37
     capable
    0.37
     Shakespeare
    0.36
    and
    0.36
    sentiment
    0.36
    POSITIVE LOGITS
    যদিও
    0.50
    Fence
    0.45
    解决方法
    0.44
    餌
    0.44
     workaround
    0.43
    icione
    0.42
     Після
    0.42
     느낌
    0.42
    饵
    0.42
    ግብ
    0.41
    Act Density 0.018%

    No Known Activations