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

    Neuronpedia

    INDEX
    Explanations

    table

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Jason
    -0.08
     Naomi
    -0.07
    .Animation
    -0.06
     Lair
    -0.06
    ελ
    -0.06
    Larry
    -0.06
     Jame
    -0.06
    arming
    -0.06
     Rebecca
    -0.06
    TECTION
    -0.06
    POSITIVE LOGITS
    ixo
    0.07
    .Flags
    0.06
    庫
    0.06
     九
    0.06
     мяг
    0.06
    寻
    0.06
    _fid
    0.06
     serv
    0.06
    荐
    0.06
    PID
    0.06
    Act Density 0.010%

    No Known Activations