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

    Neuronpedia

    INDEX
    Explanations

    colons/equal signs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Columbus
    -0.08
     Hind
    -0.07
     cris
    -0.07
    Ensure
    -0.07
    营运
    -0.07
    .brand
    -0.07
    -century
    -0.07
    кус
    -0.07
     Hu
    -0.06
     Hyundai
    -0.06
    POSITIVE LOGITS
    ሴ
    0.08
     להתמוד
    0.07
     epith
    0.07
    YLeaf
    0.07
    Editing
    0.07
    Ƭ
    0.07
    小心翼翼
    0.07
     whispered
    0.07
    Observer
    0.07
     одеж
    0.07
    Act Density 0.027%

    No Known Activations