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

    Neuronpedia

    INDEX
    Explanations

    F

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     environment
    0.54
     environments
    0.52
    環境
    0.49
     prostředí
    0.48
     ympä
    0.48
    ச்சூழ
    0.46
    Environ
    0.45
    环境
    0.43
     środow
    0.43
     air
    0.43
    POSITIVE LOGITS
    """
    0.43
    "${
    0.42
    "\
    0.41
    "",
    0.40
    ьер
    0.38
    "/
    0.38
    "_
    0.38
    metro
    0.38
    "$
    0.38
    esis
    0.38
    Act Density 0.001%

    No Known Activations