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

    Neuronpedia

    INDEX
    Explanations

    parenthesis

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Beam
    -0.07
    作坊
    -0.07
     Basically
    -0.07
     włosów
    -0.07
    _RAM
    -0.07
    限定
    -0.07
     rhe
    -0.07
     dramas
    -0.07
    ryo
    -0.07
    	UP
    -0.07
    POSITIVE LOGITS
    撤
    0.07
     ;;
    0.07
    �
    0.07
    ….↵↵
    0.06
    웨
    0.06
     SetLastError
    0.06
    xf
    0.06
    食欲
    0.06
     hasattr
    0.06
    (sizeof
    0.06
    Act Density 0.013%

    No Known Activations