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

    Neuronpedia

    INDEX
    Explanations

    more

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ovaných
    -0.07
    Sweden
    -0.06
    _swap
    -0.06
    System
    -0.06
     deported
    -0.06
    GRP
    -0.06
     sampled
    -0.06
     кан
    -0.06
     Sweden
    -0.06
     характер
    -0.06
    POSITIVE LOGITS
     potentials
    0.07
    条件
    0.07
     cres
    0.07
    .cwd
    0.07
     ödeme
    0.06
    (wait
    0.06
     Cobra
    0.06
    _opt
    0.06
    代理
    0.06
    ...");↵↵
    0.06
    Act Density 0.025%

    No Known Activations