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

    Neuronpedia

    INDEX
    Explanations

    many

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Bc
    -0.08
     botella
    -0.08
    bies
    -0.08
    parator
    -0.08
    писание
    -0.08
    年月
    -0.07
     bens
    -0.07
     nhật
    -0.07
     kali
    -0.07
    umno
    -0.07
    POSITIVE LOGITS
     manieren
    0.11
     ways
    0.10
     способов
    0.10
     способы
    0.10
     reasons
    0.10
     существуют
    0.10
     maneiras
    0.10
     Gründe
    0.10
     Möglichkeiten
    0.10
     existen
    0.10
    Act Density 0.072%

    No Known Activations