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

    Neuronpedia

    INDEX
    Explanations

    dwarf

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     financières
    -0.79
     énergé
    -0.77
     sexuales
    -0.77
     automatiques
    -0.77
     FetchType
    -0.76
     supérieurs
    -0.76
     chré
    -0.76
     chimiques
    -0.73
     ainfi
    -0.73
     normaux
    -0.73
    POSITIVE LOGITS
    ness
    0.73
    🏻
    0.54
    LookAnd
    0.50
    FieldBuilder
    0.50
     mend
    0.49
    ting
    0.49
    ly
    0.48
    Enllaces
    0.48
    sp
    0.48
    st
    0.48
    Act Density 0.120%

    No Known Activations