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

    Neuronpedia

    INDEX
    Explanations

    _key

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ixon
    -0.08
    返乡
    -0.08
     Agility
    -0.08
    moil
    -0.07
    שק
    -0.07
    /text
    -0.07
     Good
    -0.07
    丝
    -0.07
    Ū
    -0.07
     (("
    -0.07
    POSITIVE LOGITS
    dated
    0.08
    quoted
    0.08
     Albany
    0.08
     dictate
    0.07
     Hentai
    0.07
    customers
    0.07
     predecess
    0.07
    בלע
    0.07
    extracomment
    0.07
    ![↵
    0.07
    Act Density 0.000%

    No Known Activations