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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     equivalents
    -0.06
     turned
    -0.06
    [U
    -0.06
     calculations
    -0.06
    .paper
    -0.06
     Burb
    -0.06
     sdk
    -0.06
    .convert
    -0.06
    Tables
    -0.06
     esp
    -0.06
    POSITIVE LOGITS
     Elevated
    0.06
    ENOMEM
    0.06
     особлив
    0.06
     successive
    0.06
    °}
    0.06
     друго
    0.06
    値
    0.06
     світі
    0.06
    ΗΝ
    0.06
    /platform
    0.06
    Act Density 0.259%

    No Known Activations