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

    Neuronpedia

    INDEX
    Explanations

    LGBTQ+ rights and issues

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    /
    0.48
     and
    0.47
     kec
    0.47
    =""
    0.45
     Quanto
    0.43
     Cayenne
    0.43
     יותר
    0.41
     &
    0.41
     و
    0.41
     naw
    0.41
    POSITIVE LOGITS
    󠁴
    0.51
     newToken
    0.46
    生效
    0.41
    ಿಂತ
    0.41
     তাড়
    0.41
     teinture
    0.41
    newToken
    0.40
    addSprite
    0.39
    ꉂ
    0.39
     fam
    0.38
    Act Density 0.003%

    No Known Activations