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

    Neuronpedia

    INDEX
    Explanations

    /plain

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     chess
    -0.07
     Teen
    -0.06
    ificado
    -0.06
    ющим
    -0.06
    상을
    -0.06
    help
    -0.06
     dnů
    -0.06
    .mo
    -0.06
    睛
    -0.06
    etas
    -0.06
    POSITIVE LOGITS
     AABB
    0.06
    [curr
    0.06
    ро
    0.06
    „D
    0.06
    ува
    0.06
    istol
    0.06
     renewables
    0.06
    ([]);↵↵
    0.06
     휴
    0.06
    ứa
    0.06
    Act Density 0.000%

    No Known Activations