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

    Neuronpedia

    INDEX
    Explanations

    beautiful, outstanding, fantastic

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ுத
    0.54
    on
    0.53
    есть
    0.47
     undetermined
    0.46
    ০
    0.43
    of
    0.43
    iklet
    0.43
    要想
    0.42
     dons
    0.42
     stesso
    0.42
    POSITIVE LOGITS
    งาม
    0.56
    ਸ
    0.51
    টি
    0.49
    𝐞
    0.49
    𝓐
    0.48
     спорта
    0.48
    ේශ
    0.48
    🆕
    0.47
     nrow
    0.46
     والر
    0.45
    Act Density 0.396%

    No Known Activations