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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Act
    -0.07
    Hist
    -0.07
    Blood
    -0.07
    813
    -0.07
     nine
    -0.07
     Acts
    -0.07
    Ath
    -0.07
    nicas
    -0.07
    812
    -0.06
    IPA
    -0.06
    POSITIVE LOGITS
    RESET
    0.06
    presso
    0.06
    �蛛
    0.06
    >If
    0.06
    /change
    0.05
     zus
    0.05
    ="../../
    0.05
    .strip
    0.05
    ennen
    0.05
     EOS
    0.05
    Act Density 0.233%

    No Known Activations