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

    Neuronpedia

    INDEX
    Explanations

    French names

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     élevés
    -0.46
     fidé
    -0.45
     élo
    -0.41
     CHtml
    -0.41
     fidélité
    -0.41
    ggia
    -0.41
     ODS
    -0.40
     hâte
    -0.40
    //
    -0.39
    dersfield
    -0.39
    POSITIVE LOGITS
     Des
    0.52
     Lab
    0.50
     DUB
    0.50
     Dub
    0.50
     Leb
    0.49
    Lab
    0.49
    -
    0.48
     Del
    0.48
    Leroy
    0.47
     DEL
    0.47
    Act Density 0.006%

    No Known Activations