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

    Neuronpedia

    INDEX
    Explanations

    send

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     tatsäch
    -0.07
    örper
    -0.07
    찔
    -0.07
     werk
    -0.07
     tink
    -0.07
     потер
    -0.07
    疁
    -0.07
    xea
    -0.07
    ꒵
    -0.06
    鄑
    -0.06
    POSITIVE LOGITS
    (rt
    0.07
    ור
    0.07
    QU
    0.07
    ==
    0.07
     esa
    0.07
    _fds
    0.07
     grep
    0.07
    grep
    0.07
    (and
    0.07
    则是
    0.07
    Act Density 0.007%

    No Known Activations