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

    Neuronpedia

    INDEX
    Explanations

    (

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    蓠
    -0.08
    ていない
    -0.07
    !!!
    -0.07
     Plus
    -0.07
     distraction
    -0.07
     nog
    -0.07
    ều
    -0.06
    ếc
    -0.06
    してる
    -0.06
     여러분
    -0.06
    POSITIVE LOGITS
    -terminal
    0.08
    Commit
    0.08
     }];↵↵
    0.07
     subscriptions
    0.07
    EM
    0.07
    领袖
    0.07
    alogy
    0.07
     Gauss
    0.07
    农历
    0.07
    .weather
    0.07
    Act Density 0.066%

    No Known Activations