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

    Neuronpedia

    INDEX
    Explanations

    span

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     đốc
    -0.06
    invisible
    -0.06
    ิดต
    -0.06
    obbled
    -0.06
    erap
    -0.06
    ensing
    -0.06
    gif
    -0.06
     screened
    -0.06
     aired
    -0.06
    isd
    -0.06
    POSITIVE LOGITS
    _CART
    0.07
     Civ
    0.07
     близько
    0.06
    坐在
    0.06
     IHttp
    0.06
    LAS
    0.06
     ws
    0.06
     Extend
    0.06
    allows
    0.06
     payouts
    0.06
    Act Density 0.000%

    No Known Activations