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

    Neuronpedia

    INDEX
    Explanations

    supra-

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    e
    -0.72
    ability
    -0.69
    ed
    -0.69
    able
    -0.68
    eo
    -0.65
    eer
    -0.64
    eed
    -0.62
    a
    -0.60
    o
    -0.60
     bulk
    -0.60
    POSITIVE LOGITS
    ("]");
    0.60
    writeFieldEnd
    0.57
    outchouc
    0.57
    rrggbb
    0.56
    MLLoader
    0.55
     typelib
    0.54
    istible
    0.53
    etheless
    0.52
    GHIJKLM
    0.51
    phorbia
    0.51
    Act Density 0.277%

    No Known Activations