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

    Neuronpedia

    INDEX
    Explanations

    listing things

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Decade
    0.98
     Cuisine
    0.97
     Few
    0.95
     Degree
    0.93
     Pattern
    0.93
     Gender
    0.90
     Fertility
    0.90
     Color
    0.89
     Animation
    0.86
     Dependence
    0.86
    POSITIVE LOGITS
    RO
    0.78
    RV
    0.74
     объяви
    0.72
    nachweise
    0.71
     negoci
    0.71
    RA
    0.69
    北大
    0.69
    ú
    0.68
     adjuster
    0.68
     आईसीआर
    0.68
    Act Density 0.000%

    No Known Activations