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

    Neuronpedia

    INDEX
    Explanations

    unequivocally wrong

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ﭼ
    0.52
    㞱
    0.44
    MSA
    0.43
     ойнотуу
    0.42
    ாரா
    0.41
    шча
    0.41
    Pho
    0.40
     הר
    0.40
    ಖ್ಯ
    0.39
    tbx
    0.39
    POSITIVE LOGITS
     dominance
    0.45
    配
    0.42
     spider
    0.41
     स्थायी
    0.38
     स्थाई
    0.38
     unequiv
    0.38
     snake
    0.37
     thin
    0.36
    spider
    0.36
     weeds
    0.36
    Act Density 0.001%

    No Known Activations