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

    Neuronpedia

    INDEX
    Explanations

    language diacritics

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     covariance
    -0.09
    毕业
    -0.07
    />";↵
    -0.07
    sled
    -0.07
    .state
    -0.07
     épa
    -0.07
     sonhos
    -0.07
    -real
    -0.07
     Sunset
    -0.07
     Lago
    -0.07
    POSITIVE LOGITS
     correspondiente
    0.11
     correspondente
    0.11
     correspon
    0.10
     correspondientes
    0.10
     serait
    0.09
     cramped
    0.09
     counterparts
    0.09
    对应
    0.08
     would've
    0.08
     selectable
    0.08
    Act Density 0.009%

    No Known Activations