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

    Neuronpedia

    INDEX
    Explanations

    first of many

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _acc
    -0.07
     pinterest
    -0.07
    アン
    -0.06
     SOME
    -0.06
    PC
    -0.06
     Ahmed
    -0.06
    Apellido
    -0.06
    оне
    -0.06
     с
    -0.06
    氏
    -0.06
    POSITIVE LOGITS
    moth
    0.07
    .Boolean
    0.07
    letic
    0.06
    ellites
    0.06
     čist
    0.06
    ernote
    0.06
    要
    0.06
    릴
    0.06
    ρω
    0.05
     tiêu
    0.05
    Act Density 0.044%

    No Known Activations