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

    Neuronpedia

    INDEX
    Explanations

    periods

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     heißt
    -0.07
    年以上
    -0.07
     launder
    -0.07
    벳
    -0.07
    国籍
    -0.07
    YO
    -0.06
     mell
    -0.06
    מסמ
    -0.06
    であり
    -0.06
    -earth
    -0.06
    POSITIVE LOGITS
     Executors
    0.08
     Advances
    0.07
    plugins
    0.07
    LEC
    0.07
    .Public
    0.07
    二
    0.07
     genus
    0.07
    lices
    0.07
    Restart
    0.07
    (system
    0.07
    Act Density 0.031%

    No Known Activations