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

    Neuronpedia

    INDEX
    Explanations

    commas

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    CM
    -0.07
    ése
    -0.06
    fin
    -0.06
    mó
    -0.06
    dirname
    -0.06
    젡
    -0.06
    ｍ
    -0.06
    eo
    -0.06
    协会
    -0.06
    rew
    -0.06
    POSITIVE LOGITS
    也是如此
    0.08
    /general
    0.07
     Genç
    0.07
    (print
    0.07
    .loaded
    0.07
     Strings
    0.07
    和个人
    0.07
    Wrapped
    0.07
     tutoring
    0.06
    Enumeration
    0.06
    Act Density 0.056%

    No Known Activations