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

    Neuronpedia

    INDEX
    Explanations

    . , 0 , 3 , X , right , taller , write

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ఙ
    0.91
    有可能
    0.83
    ন
    0.82
    ến
    0.79
    णी
    0.77
    nof
    0.75
    moy
    0.72
    عيد
    0.71
    ේෂ
    0.70
    竝
    0.70
    POSITIVE LOGITS
     этот
    0.76
     ette
    0.73
    ቱን
    0.71
     Этот
    0.70
    、
    0.68
    ፣
    0.68
     эту
    0.66
     kerana
    0.65
    ORE
    0.64
    >&
    0.64
    Act Density 0.003%

    No Known Activations