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

    Neuronpedia

    INDEX
    Explanations

    saying, "why", "looks"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     fractional
    0.36
     L
    0.35
     parchment
    0.35
     psychic
    0.34
     accessories
    0.34
     일반적으로
    0.34
     fragments
    0.33
     également
    0.33
     trails
    0.32
     vitality
    0.32
    POSITIVE LOGITS
    why
    0.48
     queremos
    0.46
     кто
    0.45
    Hey
    0.44
    Мы
    0.44
    Estoy
    0.44
    だったら
    0.44
    Why
    0.43
    我要
    0.43
     నేను
    0.42
    Act Density 0.147%

    No Known Activations