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

    Neuronpedia

    INDEX
    Explanations

    following

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Employ
    -0.07
     auth
    -0.06
    INTER
    -0.06
    /layouts
    -0.06
     Mt
    -0.06
     oz
    -0.06
     پخش
    -0.06
     Cou
    -0.06
     trois
    -0.06
     hotel
    -0.06
    POSITIVE LOGITS
    ));↵↵↵
    0.07
     disqualified
    0.07
    inke
    0.07
     stimulates
    0.06
     underwater
    0.06
     ```
    0.06
     〈
    0.06
    ！！
    0.06
    awan
    0.06
    Figure
    0.06
    Act Density 0.005%

    No Known Activations