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

    Neuronpedia

    INDEX
    Explanations

    master

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    pref
    -0.06
     kuk
    -0.06
     �
    -0.06
     Reuters
    -0.05
     家
    -0.05
     Unicorn
    -0.05
    xea
    -0.05
    ahi
    -0.05
     Fireplace
    -0.05
    เอง
    -0.05
    POSITIVE LOGITS
     dernière
    0.08
    `↵
    0.07
     nhiễm
    0.07
    cp
    0.07
    -fix
    0.07
    发生
    0.07
     numberOf
    0.07
     threading
    0.07
    CHECK
    0.07
     handler
    0.07
    Act Density 0.003%

    No Known Activations