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

    Neuronpedia

    INDEX
    Explanations

    lists of pros

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Structure
    0.45
     Struktur
    0.44
    rolo
    0.43
     Bedarf
    0.42
     Mechanism
    0.41
    appreci
    0.40
     热
    0.40
     Sistemi
    0.40
     excelled
    0.40
    űkö
    0.39
    POSITIVE LOGITS
     لیکن
    0.44
     campground
    0.43
    codon
    0.42
     אבל
    0.40
     gulf
    0.40
     but
    0.40
     similit
    0.40
     fortune
    0.40
     руководство
    0.40
     uninformed
    0.40
    Act Density 0.031%

    No Known Activations