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

    Neuronpedia

    INDEX
    Explanations

    non-sentences

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     pervasive
    -0.07
    fid
    -0.07
     outputStream
    -0.07
    規
    -0.07
     vacant
    -0.06
     próximo
    -0.06
     statutes
    -0.06
     Ambient
    -0.06
    POSIT
    -0.06
     maze
    -0.06
    POSITIVE LOGITS
    혀
    0.07
    /--
    0.06
    ن
    0.06
    arme
    0.06
    ﾊ
    0.06
     инт
    0.06
    reo
    0.06
     aktiv
    0.06
    YYY
    0.06
    희
    0.06
    Act Density 0.132%

    No Known Activations