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

    Neuronpedia

    INDEX
    Explanations

    relationships

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Denied
    -0.07
    ’ét
    -0.07
     '~/
    -0.07
    Claims
    -0.07
    ‌س
    -0.07
    oling
    -0.07
     china
    -0.06
    opts
    -0.06
     Seeds
    -0.06
     '((
    -0.06
    POSITIVE LOGITS
     organise
    0.06
    调查
    0.06
     منطقه
    0.06
     vä
    0.06
    ，並
    0.06
    ेदन
    0.06
    ())
    0.06
    μερο
    0.06
     گفته
    0.06
    λαν
    0.06
    Act Density 0.057%

    No Known Activations