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

    Neuronpedia

    INDEX
    Explanations

    regex start anchors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     deceiving
    0.64
     viviendo
    0.64
     pełni
    0.59
    ব
    0.56
     cuáles
    0.56
    cus
    0.56
    ম
    0.55
    кры
    0.54
    fichier
    0.53
    꿋
    0.53
    POSITIVE LOGITS
    稹
    0.69
    ურთ
    0.67
     eest
    0.59
    istel
    0.58
     shovel
    0.58
    |\
    0.58
     shov
    0.58
     combinatorial
    0.57
     entails
    0.57
    ב
    0.57
    Act Density 0.019%

    No Known Activations