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

    Neuronpedia

    INDEX
    Explanations

    silver

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .fil
    -0.07
     wrestler
    -0.07
    시험
    -0.07
    生产能力
    -0.07
    مد
    -0.07
    iland
    -0.07
    _ELEM
    -0.07
     adamant
    -0.06
    ————
    -0.06
    olv
    -0.06
    POSITIVE LOGITS
    Ȳ
    0.08
     approach
    0.07
    واس
    0.07
    (code
    0.07
    }`,
    0.07
    bound
    0.07
     atenção
    0.07
    tain
    0.07
    ,strlen
    0.07
     Taipei
    0.07
    Act Density 0.004%

    No Known Activations