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

    Neuronpedia

    INDEX
    Explanations

    for

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _AT
    -0.07
     suction
    -0.07
    щей
    -0.06
    ียนบ
    -0.06
    мещ
    -0.06
     extremism
    -0.06
    -ब
    -0.06
    .inline
    -0.06
     시스템
    -0.06
     fibre
    -0.06
    POSITIVE LOGITS
     give
    0.06
    breaking
    0.06
     Coin
    0.06
     Final
    0.06
    mun
    0.06
     ButterKnife
    0.06
     jails
    0.06
     Crimson
    0.06
    .Update
    0.06
     honors
    0.06
    Act Density 0.004%

    No Known Activations