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

    Neuronpedia

    INDEX
    Explanations

    induced damage

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Госп
    -0.07
     enhancing
    -0.06
    Touches
    -0.06
     Bootstrap
    -0.06
     strengthening
    -0.06
    -ios
    -0.06
     Enlightenment
    -0.06
    .launch
    -0.06
    Pocket
    -0.06
    诊
    -0.06
    POSITIVE LOGITS
    ……
    0.07
     []↵
    0.07
     question
    0.06
    linky
    0.06
     curly
    0.06
    ';↵↵↵
    0.06
     toJSON
    0.06
    ↵
↵
    0.06
    ernaut
    0.06
    ья
    0.06
    Act Density 0.046%

    No Known Activations