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

    Neuronpedia

    INDEX
    Explanations

    introducing examples

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    த்
    0.94
    তিনি
    0.85
     beiden
    0.84
     sebelah
    0.83
     Secara
    0.81
    од
    0.81
    दो
    0.79
     tucked
    0.79
     هناك
    0.78
     Bahkan
    0.76
    POSITIVE LOGITS
     as
    1.61
    like
    1.59
     kuin
    1.37
    जैसे
    1.33
     כמו
    1.29
     например
    1.28
     like
    1.26
    Like
    1.24
     como
    1.22
     như
    1.18
    Act Density 0.028%

    No Known Activations