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

    Neuronpedia

    INDEX
    Explanations

    Cyrillic/punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Vladimir
    -0.32
     Vlad
    -0.30
    agina
    -0.28
     Dmit
    -0.28
     Ukr
    -0.27
    sez
    -0.26
    avr
    -0.26
    交æį¢
    -0.26
     Soviets
    -0.26
    ilater
    -0.26
    POSITIVE LOGITS
    idata
    0.31
    缸åĬ©
    0.29
    minor
    0.29
    麻辣
    0.28
    Minor
    0.27
    dio
    0.26
     quanto
    0.26
     Minor
    0.25
    è¿Ļç§įäºĭæĥħ
    0.24
    alth
    0.24
    Act Density 0.022%

    No Known Activations