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

    Neuronpedia

    INDEX
    Explanations

    anymore comes from lies

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ausgezeichnet
    0.54
    ，
    0.54
     stoff
    0.51
    之旅
    0.50
     eluted
    0.50
    一百
    0.49
    ᄐ
    0.49
     flavonoids
    0.49
     Schweizer
    0.48
     glycoproteins
    0.48
    POSITIVE LOGITS
    یه
    0.52
    isan
    0.49
    ுள்ள
    0.46
    یان
    0.44
    ]=
    0.43
    en
    0.42
    ียน
    0.42
    িং
    0.41
     삶
    0.40
    Checksum
    0.40
    Act Density 0.000%

    No Known Activations