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

    Neuronpedia

    INDEX
    Explanations

    company suffixes like Inc. or Ltd

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Leibn
    0.45
    လိုအပ်
    0.44
     Tokugawa
    0.42
     glycerol
    0.40
     menny
    0.39
     Sq
    0.39
     Comte
    0.39
     Takah
    0.39
     స్థాయిలో
    0.39
     Syl
    0.39
    POSITIVE LOGITS
    ’
    0.49
    ž
    0.48
    상
    0.47
    ”
    0.46
    ار
    0.44
    اب
    0.44
    ारा
    0.44
    riam
    0.43
    ala
    0.43
    asına
    0.42
    Act Density 0.007%

    No Known Activations