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

    Neuronpedia

    INDEX
    Explanations

    Social media feeds

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ray
    -0.06
     character
    -0.06
     prayer
    -0.06
     USD
    -0.06
     CreateMap
    -0.06
    _scan
    -0.06
     $.
    -0.06
    σκ
    -0.06
    Tau
    -0.06
    349
    -0.06
    POSITIVE LOGITS
     Passenger
    0.07
    _gr
    0.07
    统
    0.07
     chiế
    0.06
     대
    0.06
     retrospective
    0.06
     Pass
    0.06
    -bl
    0.06
     現
    0.06
     Albuquerque
    0.06
    Act Density 0.064%

    No Known Activations