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

    Neuronpedia

    INDEX
    Explanations

    explicitly specify

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ஸி
    0.41
    sommets
    0.39
     lights
    0.38
    গানি
    0.38
     tabby
    0.38
    Посилання
    0.37
    lights
    0.37
     champignons
    0.37
     lumen
    0.36
    currentPlayer
    0.36
    POSITIVE LOGITS
     explicitly
    0.63
     지정
    0.59
    explicit
    0.58
     explicit
    0.57
     설정
    0.56
     specify
    0.55
    指定
    0.55
    Explicit
    0.55
    选项
    0.54
     opção
    0.54
    Act Density 0.172%

    No Known Activations