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

    Neuronpedia

    INDEX
    Explanations

    Code/Configurations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Azerbai
    -0.09
     βιβ
    -0.06
     \`
    -0.06
     вал
    -0.06
    ot
    -0.06
     downt
    -0.06
     ecstasy
    -0.06
     cancellationToken
    -0.06
     summoned
    -0.06
    写
    -0.06
    POSITIVE LOGITS
    CTYPE
    0.06
     Legion
    0.06
    LEncoder
    0.06
     powerful
    0.06
     спад
    0.06
    Ｔ
    0.06
     سرد
    0.06
    Eval
    0.06
    George
    0.06
    (H
    0.06
    Act Density 0.035%

    No Known Activations