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

    Neuronpedia

    INDEX
    Explanations

    like all/any/other

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Normally
    0.46
     പിന്നീട്
    0.45
     filmpje
    0.43
    Normally
    0.43
     Beit
    0.43
     vemos
    0.43
     ഇങ്ങനെ
    0.43
    يك
    0.42
     Opin
    0.41
    ьому
    0.41
    POSITIVE LOGITS
    га
    0.42
    *
    0.40
    н
    0.38
    att
    0.37
     richard
    0.37
    뿐
    0.36
    DA
    0.36
    나
    0.36
    sad
    0.36
     others
    0.36
    Act Density 0.013%

    No Known Activations