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

    Neuronpedia

    INDEX
    Explanations

    category column

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     건강
    0.44
     হলুদ
    0.42
     ಮೂಲ
    0.41
    overleftarrow
    0.40
    itemBackground
    0.39
     ಟ
    0.38
     dopamine
    0.38
     하시
    0.38
     아이
    0.38
    acritic
    0.38
    POSITIVE LOGITS
    える
    0.39
    ۪
    0.39
     Erg
    0.37
    рій
    0.36
    度に
    0.36
     Mathew
    0.36
     debris
    0.35
    れない
    0.35
     Fiction
    0.35
     slee
    0.34
    Act Density 0.208%

    No Known Activations