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

    Neuronpedia

    INDEX
    Explanations

    Non-English language

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ())
↵
↵
    -0.06
    _score
    -0.06
     Sith
    -0.06
    лл
    -0.06
     Dou
    -0.06
    ћ
    -0.06
    深
    -0.06
    .tests
    -0.06
     ape
    -0.06
     Spells
    -0.06
    POSITIVE LOGITS
     listed
    0.07
     Genuine
    0.07
     implements
    0.07
     junction
    0.06
     aggi
    0.06
     затвердж
    0.06
    notated
    0.06
     materia
    0.06
     zpracování
    0.06
     predic
    0.06
    Act Density 0.042%

    No Known Activations