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

    Neuronpedia

    INDEX
    Explanations

    reasonable number

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     মর্যা
    0.90
     бед
    0.85
     imbalance
    0.83
    akkam
    0.80
     habitats
    0.79
     forms
    0.78
     discoveries
    0.78
     fingertips
    0.78
     accident
    0.77
     মর্যাদা
    0.77
    POSITIVE LOGITS
    Enough
    0.92
    Personal
    0.92
    branch
    0.81
    Hir
    0.80
    Branch
    0.78
    personal
    0.78
     กี่
    0.77
    데요
    0.77
     ब्रांच
    0.76
    Brom
    0.75
    Act Density 0.000%

    No Known Activations