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

    Neuronpedia

    INDEX
    Explanations

    months and words of positive reinforcement

    oai_token-act-pair · gemini-2.0-flash

    months

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Dec
    -2.02
     Aug
    -1.95
    Dec
    -1.95
     Oct
    -1.83
    Aug
    -1.81
    Oct
    -1.80
     Jan
    -1.80
     Nov
    -1.79
    Nov
    -1.74
    Jan
    -1.70
    POSITIVE LOGITS
    XmlType
    0.67
     &___
    0.63
     transférez
    0.63
    RectangleBorder
    0.62
    setVerticalGroup
    0.61
    InputBorder
    0.57
     SIMBAD
    0.56
    libft
    0.52
    anneer
    0.48
    exercice
    0.48
    Act Density 6.765%

    No Known Activations