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
     stunned
    -0.07
    عداد
    -0.07
     tượng
    -0.07
    _tweets
    -0.06
     veloc
    -0.06
     plata
    -0.06
     evac
    -0.06
    עס
    -0.06
     Paz
    -0.06
    LineWidth
    -0.06
    POSITIVE LOGITS
    .test
    0.07
    绝不
    0.07
     Consequently
    0.07
     사실
    0.07
    溢价
    0.07
    Conexion
    0.06
    璇
    0.06
    enterprise
    0.06
    -vertical
    0.06
     רחב
    0.06
    Act Density 0.000%

    No Known Activations