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

    Neuronpedia

    INDEX
    Explanations

    Son

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    HIGH
    -0.08
     '../../../
    -0.07
    创新
    -0.07
     mig
    -0.06
    
    -0.06
     france
    -0.06
     Rail
    -0.06
     Zoom
    -0.06
                   ↵
    -0.06
     ITV
    -0.06
    POSITIVE LOGITS
     Son
    0.18
    son
    0.17
     son
    0.17
    Son
    0.17
     Sons
    0.14
    SON
    0.14
     SON
    0.14
     sons
    0.13
     Jon
    0.10
    сон
    0.10
    Act Density 0.021%

    No Known Activations