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

    Neuronpedia

    INDEX
    Explanations

    Slavic and English words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    肨
    0.39
     поді
    0.38
     variante
    0.37
    อป
    0.36
     Usage
    0.36
    pImage
    0.36
     Building
    0.35
     بكم
    0.35
     Tent
    0.34
     точка
    0.34
    POSITIVE LOGITS
    𝓻
    0.46
    pair
    0.43
    urés
    0.41
    ွန်
    0.39
     Butler
    0.39
     dział
    0.39
    Butler
    0.39
    pairs
    0.38
     afect
    0.38
    Part
    0.37
    Act Density 0.002%

    No Known Activations