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

    Neuronpedia

    INDEX
    Explanations

    because

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Agents
    -0.08
    endo
    -0.08
    第一届
    -0.08
    prises
    -0.07
    +,
    -0.07
    件
    -0.07
     će
    -0.06
    規
    -0.06
    tee
    -0.06
     Manager
    -0.06
    POSITIVE LOGITS
     adequately
    0.07
     OSD
    0.07
     Indeed
    0.07
    glob
    0.07
     OW
    0.07
     meanwhile
    0.06
    �
    0.06
    全
    0.06
     terrible
    0.06
     sob
    0.06
    Act Density 0.037%

    No Known Activations