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

    Neuronpedia

    INDEX
    Explanations

    as

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     diplomats
    -0.07
    Marshal
    -0.07
     เขต
    -0.07
     Ram
    -0.07
    Pane
    -0.07
    emen
    -0.07
    fur
    -0.07
     большин
    -0.06
    ились
    -0.06
     ذ
    -0.06
    POSITIVE LOGITS
    千
    0.07
     ジャ
    0.06
    enville
    0.06
    mah
    0.06
    ejs
    0.06
    etroit
    0.06
    лаж
    0.06
    .TrimSpace
    0.06
     Playback
    0.05
     dh
    0.05
    Act Density 0.001%

    No Known Activations