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

    Neuronpedia

    INDEX
    Explanations

    technical writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Benef
    -0.07
     Earl
    -0.07
     Farrell
    -0.07
     executed
    -0.07
     Feder
    -0.07
    .spawn
    -0.07
     여러분
    -0.07
    .Element
    -0.07
     canon
    -0.06
     Won
    -0.06
    POSITIVE LOGITS
    沼
    0.07
    不稳定
    0.07
    額
    0.07
     yüzden
    0.07
    =-=-
    0.07
    גורמים
    0.07
    支出
    0.07
    没人
    0.06
    势
    0.06
    .Uri
    0.06
    Act Density 0.676%

    No Known Activations