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

    Neuronpedia

    INDEX
    Explanations

    seen so

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    у
    0.91
    і
    0.89
    श
    0.87
    id
    0.85
    begin
    0.85
    ien
    0.79
    í
    0.77
    о
    0.75
    ну
    0.74
    q
    0.74
    POSITIVE LOGITS
     Scrolls
    0.80
    Mét
    0.79
     Cinemas
    0.77
    टेन
    0.74
    İL
    0.74
    ²',
    0.73
     ²
    0.73
     טוב
    0.72
    Achievements
    0.72
     মোহাম্মদ
    0.71
    Act Density 0.000%

    No Known Activations