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

    Neuronpedia

    INDEX
    Explanations

    describing context or clarification

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ت
    0.60
    abon
    0.44
    c
    0.43
    summer
    0.43
    W
    0.42
    ли
    0.41
    athery
    0.41
    t
    0.40
    ர்
    0.39
    nickel
    0.39
    POSITIVE LOGITS
     उपा
    0.46
     തി
    0.44
     bagged
    0.41
     replacement
    0.41
    小姐
    0.41
     দফা
    0.41
     rejoined
    0.41
     Redmond
    0.40
     ఏ
    0.39
    ご注意
    0.39
    Act Density 0.007%

    No Known Activations