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

    Neuronpedia

    INDEX
    Explanations

    Code/Configuration files

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    /head
    -0.07
     Sword
    -0.07
     infant
    -0.07
     Chill
    -0.06
     Blade
    -0.06
     Angie
    -0.06
    ker
    -0.06
     rubbed
    -0.06
    (be
    -0.06
     serum
    -0.06
    POSITIVE LOGITS
    _Admin
    0.07
     당
    0.07
    ськ
    0.07
    ้าน
    0.06
     รอบ
    0.06
    (builder
    0.06
    ΑΤ
    0.06
    -प
    0.06
     základní
    0.06
    ?“↵↵
    0.06
    Act Density 0.009%

    No Known Activations