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

    Neuronpedia

    INDEX
    Explanations

    code expressions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    르는
    -0.07
     youre
    -0.07
    .Dataset
    -0.06
    handle
    -0.06
    .Doc
    -0.06
     stance
    -0.06
     onRequest
    -0.06
    quate
    -0.06
     OTHERWISE
    -0.06
     beaucoup
    -0.06
    POSITIVE LOGITS
     subscribers
    0.07
    647
    0.06
    638
    0.06
     Wordpress
    0.06
     Bruno
    0.06
    ERCHANTABILITY
    0.06
    .instagram
    0.06
    Direccion
    0.06
     kür
    0.06
     떠
    0.06
    Act Density 0.038%

    No Known Activations