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

    Neuronpedia

    INDEX
    Explanations

    married

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Hendrix
    -0.08
     habitu
    -0.08
    ROWSER
    -0.08
     Himself
    -0.08
     pur
    -0.08
    .orange
    -0.08
     tikanga
    -0.07
     realidade
    -0.07
    irties
    -0.07
     emocion
    -0.07
    POSITIVE LOGITS
     Stateless
    0.09
    �
    0.08
    Median
    0.08
     Median
    0.07
    assuming
    0.07
     arbitr
    0.07
     célib
    0.07
    Processing
    0.07
     processing
    0.07
    Singleton
    0.07
    Act Density 0.006%

    No Known Activations