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

    Neuronpedia

    INDEX
    Explanations

    actor

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     méthode
    -0.06
    =$((
    -0.06
    сок
    -0.06
     Gron
    -0.06
    noinspection
    -0.06
     Japon
    -0.06
    <Model
    -0.06
     giochi
    -0.06
    侧
    -0.06
     clazz
    -0.06
    POSITIVE LOGITS
     grievances
    0.08
     Actress
    0.07
     October
    0.07
     Tie
    0.07
     Marvel
    0.06
    ampler
    0.06
     dek
    0.06
     November
    0.06
     Instructions
    0.06
     manner
    0.06
    Act Density 0.002%

    No Known Activations