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

    Neuronpedia

    INDEX
    Explanations

    вед

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     monoc
    -0.08
    dio
    -0.08
     Oliveira
    -0.08
    Louis
    -0.08
    丝
    -0.07
     Bracelet
    -0.07
     Ane
    -0.07
    cretsiz
    -0.07
    -save
    -0.07
    otores
    -0.07
    POSITIVE LOGITS
     illusions
    0.08
     auge
    0.08
     Ban
    0.08
     çalışmalar
    0.08
     Vad
    0.07
     ban
    0.07
     calculation
    0.07
     zh
    0.07
    0.07
    esh
    0.07
    Act Density 0.002%
    No Known Activations