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

    Neuronpedia

    INDEX
    Explanations

    hubris

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ags
    0.41
     quitter
    0.39
     dispersions
    0.37
     bestand
    0.37
    ophytic
    0.37
    db
    0.36
     சூ
    0.36
    dbname
    0.36
     Ep
    0.36
    Synchron
    0.35
    POSITIVE LOGITS
     hy
    0.63
     Hy
    0.53
     Nem
    0.47
    Hy
    0.46
    hy
    0.45
    STIC
    0.43
    бри
    0.42
    スティ
    0.42
    нэ
    0.42
     hyaluronic
    0.41
    Act Density 0.000%

    No Known Activations