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

    Neuronpedia

    INDEX
    Explanations

    Williams references

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ücher
    0.52
    ਿਲ
    0.38
    ulah
    0.38
     चमक
    0.38
    िलो
    0.37
     hồng
    0.37
    thag
    0.37
     EXC
    0.37
    instant
    0.36
    കസ
    0.36
    POSITIVE LOGITS
     Sisters
    0.46
    ARTA
    0.41
     Ident
    0.40
    esses
    0.40
    spot
    0.39
     Buddhist
    0.39
     CLI
    0.39
     Bunny
    0.39
     Compan
    0.39
     Cats
    0.38
    Act Density 0.000%

    No Known Activations