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

    Neuronpedia

    INDEX
    Explanations

    code, math expressions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    据
    -0.07
     fals
    -0.07
     Greatest
    -0.06
    	message
    -0.06
    maktadır
    -0.06
     галузі
    -0.06
     bulunur
    -0.06
    弟
    -0.06
     quý
    -0.06
     huh
    -0.06
    POSITIVE LOGITS
    oves
    0.07
    ＿_
    0.06
    oge
    0.06
    .pg
    0.06
     inicio
    0.06
    shore
    0.06
    ancia
    0.06
     sandy
    0.06
    漏
    0.06
    eprom
    0.06
    Act Density 0.028%

    No Known Activations