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

    Neuronpedia

    INDEX
    Explanations

    Book

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Browser
    -0.07
     ascend
    -0.07
    笾
    -0.07
    鹂
    -0.07
     adres
    -0.07
     steroids
    -0.06
     niche
    -0.06
     Jerusalem
    -0.06
    ᵧ
    -0.06
    .stat
    -0.06
    POSITIVE LOGITS
    messages
    0.07
    setItem
    0.07
     SHOW
    0.06
     push
    0.06
    WOOD
    0.06
    plements
    0.06
    umptech
    0.06
    uição
    0.06
    reset
    0.06
     SUN
    0.06
    Act Density 0.002%

    No Known Activations