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

    Neuronpedia

    INDEX
    Explanations

    $$

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     mohla
    -0.08
    ()).
    -0.07
     Ferdinand
    -0.06
    Credits
    -0.06
     зам
    -0.06
    borrow
    -0.06
     перег
    -0.06
    ))↵↵
    -0.06
    .scal
    -0.06
     Elemental
    -0.06
    POSITIVE LOGITS
     &'
    0.08
    (chart
    0.06
    .fs
    0.06
     ld
    0.06
    -first
    0.06
    .font
    0.06
     Indianapolis
    0.06
    /use
    0.06
     Nẵng
    0.06
    uries
    0.06
    Act Density 0.005%

    No Known Activations