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

    Neuronpedia

    INDEX
    Explanations

    Mau

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    s
    -1.40
    ی
    -0.98
    awtextra
    -0.85
    e
    -0.73
    sio
    -0.72
    sı
    -0.68
    a
    -0.66
    ים
    -0.65
    BeginContext
    -0.65
    sai
    -0.65
    POSITIVE LOGITS
    herjee
    0.60
    bewerken
    0.55
     fondament
    0.54
     complètes
    0.52
     hábiles
    0.52
    érature
    0.49
    ally
    0.48
     fermés
    0.48
    rån
    0.48
    aleza
    0.48
    Act Density 0.054%

    No Known Activations