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

    Neuronpedia

    INDEX
    Explanations

    ascii art examples

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    底部
    0.41
    ===
    0.41
    ocks
    0.40
    食材
    0.40
    ock
    0.39
    rocks
    0.38
    ottom
    0.37
    crib
    0.36
    &
    0.36
    ctr
    0.36
    POSITIVE LOGITS
    și
    0.42
     خارجية
    0.40
     খায়
    0.37
     zhōng
    0.37
     కారణ
    0.36
     SHRI
    0.36
    ⠉
    0.36
    耇
    0.36
     тут
    0.36
     categoría
    0.35
    Act Density 0.011%

    No Known Activations