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

    Neuronpedia

    INDEX
    Explanations

    end

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Gram
    -0.07
     ><
    -0.07
     alternative
    -0.07
     Honestly
    -0.07
     Alternative
    -0.07
     <
    -0.07
     discour
    -0.07
    .secondary
    -0.07
    rosis
    -0.07
     undone
    -0.07
    POSITIVE LOGITS
     Dias
    0.08
     छह
    0.08
    翼
    0.08
    六
    0.08
    (?)
    0.08
    еф
    0.08
     Nong
    0.08
    -six
    0.08
    ifikasi
    0.07
    yet
    0.07
    Act Density 0.029%

    No Known Activations