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

    Neuronpedia

    INDEX
    Explanations

    here are resources

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Assessment
    0.78
     inability
    0.73
     Assessment
    0.67
    缺乏
    0.65
    保持
    0.63
     interaction
    0.61
     incapable
    0.61
     निहित
    0.61
    内容
    0.61
     Axes
    0.60
    POSITIVE LOGITS
    ulfate
    0.80
     sulfate
    0.79
     gathered
    0.79
     Dent
    0.76
     dentist
    0.76
     gleaned
    0.75
     meant
    0.75
     sempl
    0.74
     cuc
    0.74
     intended
    0.74
    Act Density 0.059%

    No Known Activations