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

    Neuronpedia

    INDEX
    Explanations

    multi-part concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    आज
    0.45
    nek
    0.42
    ünüz
    0.40
    वासन
    0.39
     વિશ્વ
    0.38
    க்கொள்ள
    0.38
    unicaciones
    0.37
     communications
    0.37
     acquire
    0.37
     आज
    0.37
    POSITIVE LOGITS
    electro
    0.42
     isomorphism
    0.40
     stitches
    0.40
    ቆዳ
    0.40
     —,
    0.39
     قل
    0.39
     vibrational
    0.39
    結晶
    0.39
     показатели
    0.38
    unstyled
    0.38
    Act Density 0.006%

    No Known Activations