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

    Neuronpedia

    INDEX
    Explanations

    's

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    aveled
    -0.06
    igure
    -0.06
     rá
    -0.06
    ustria
    -0.06
    .↵↵↵↵
    -0.06
     Möglichkeit
    -0.06
    fwrite
    -0.06
    мовір
    -0.06
    範
    -0.06
    dea
    -0.06
    POSITIVE LOGITS
    нов
    0.07
    خش
    0.07
    ―
    0.06
    침
    0.06
    ص
    0.06
    ичес
    0.06
     concentration
    0.06
     Business
    0.06
    .rx
    0.06
    β
    0.06
    Act Density 0.001%

    No Known Activations