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

    Neuronpedia

    INDEX
    Explanations

    filled with things

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    hemeral
    0.39
    ashion
    0.34
    ponente
    0.33
     চক্ষ
    0.33
     Princip
    0.33
    鉞
    0.32
    ↦
    0.32
    كمال
    0.32
     molest
    0.31
    InBackground
    0.31
    POSITIVE LOGITS
     filled
    3.13
     Filled
    2.72
    filled
    2.61
    Filled
    2.61
     lleno
    2.53
    充满了
    2.33
     llena
    2.28
    充满
    2.22
    充滿
    2.14
     напол
    1.94
    Act Density 0.110%

    No Known Activations