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

    Neuronpedia

    INDEX
    Explanations

    into

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     heads
    -0.07
    /send
    -0.06
     Merk
    -0.06
    cının
    -0.06
     arbitrarily
    -0.06
     Abyss
    -0.06
     حل
    -0.06
     voiced
    -0.06
     disputes
    -0.06
     AQ
    -0.06
    POSITIVE LOGITS
     gam
    0.07
    iously
    0.06
    roll
    0.06
    velle
    0.06
    ॰
    0.06
    선
    0.06
     Bullet
    0.06
    .intersection
    0.06
    .port
    0.06
    .pickle
    0.06
    Act Density 0.002%

    No Known Activations