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

    Neuronpedia

    INDEX
    Explanations

    affinity labeling

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ordinated
    -0.07
     Electricity
    -0.06
     Ej
    -0.06
    Labor
    -0.06
    Redux
    -0.06
    同じ
    -0.06
    omic
    -0.06
    dux
    -0.06
     GO
    -0.06
     Emil
    -0.06
    POSITIVE LOGITS
    .COM
    0.07
     khẳng
    0.06
    -_
    0.06
     factual
    0.06
     Počet
    0.06
    $client
    0.06
     Speakers
    0.06
    بین
    0.06
    帝
    0.06
    ENSITY
    0.06
    Act Density 0.023%

    No Known Activations