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

    Neuronpedia

    INDEX
    Explanations

    research paper citations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    اعي
    -0.08
     Inter
    -0.08
     inter
    -0.08
     intervenção
    -0.07
     ESG
    -0.07
    (trim
    -0.07
    illir
    -0.07
    _supply
    -0.07
     Toto
    -0.07
     alliances
    -0.07
    POSITIVE LOGITS
     seminal
    0.10
     öner
    0.09
     publicado
    0.09
     révolution
    0.09
    论文
    0.09
     pioneering
    0.09
     proposing
    0.09
     groundbreaking
    0.09
     voorstel
    0.09
    发表于
    0.08
    Act Density 0.008%

    No Known Activations