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

    Neuronpedia

    INDEX
    Explanations

    was

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Bộ
    -0.07
     matchups
    -0.07
     एक
    -0.06
     replaces
    -0.06
     takeover
    -0.06
    。その
    -0.06
     piston
    -0.06
     '}
    -0.06
     kiện
    -0.06
     Guinness
    -0.06
    POSITIVE LOGITS
    unless
    0.07
    ینک
    0.07
    anded
    0.07
     estimated
    0.06
    angered
    0.06
    ánd
    0.06
    ItemClickListener
    0.06
    bler
    0.06
    PG
    0.06
     JL
    0.06
    Act Density 0.012%

    No Known Activations