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

    Neuronpedia

    INDEX
    Explanations

    period

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    testdata
    -0.07
    爱国主义
    -0.07
    ופה
    -0.07
    .Test
    -0.07
    .Touch
    -0.07
    äs
    -0.07
     Snowden
    -0.07
    alnum
    -0.06
     INC
    -0.06
    得分
    -0.06
    POSITIVE LOGITS
     Families
    0.07
     Ser
    0.07
    Unity
    0.07
    asti
    0.07
    ח
    0.07
    Lifecycle
    0.07
     subsystem
    0.07
     tut
    0.07
    _xy
    0.06
    脚步
    0.06
    Act Density 0.002%

    No Known Activations