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

    Neuronpedia

    INDEX
    Explanations

    optional parameters followed by ):

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ⸨
    0.43
    糇
    0.42
    ስቃሴ
    0.41
     ہاتھ
    0.40
     ।*
    0.38
    钒
    0.38
    贰章
    0.38
    陘
    0.38
     محاضره
    0.38
    擔心
    0.38
    POSITIVE LOGITS
    1
    0.53
     ২৫
    0.44
     Sub
    0.42
    १
    0.39
     the
    0.38
     eleventh
    0.38
     ١
    0.37
     a
    0.36
    quot
    0.36
    ue
    0.36
    Act Density 0.006%

    No Known Activations