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

    Neuronpedia

    INDEX
    Explanations

    math expressions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Intercept
    -0.08
    >I
    -0.07
    MK
    -0.07
    隶属
    -0.07
    碼
    -0.07
    fts
    -0.06
    ….↵↵
    -0.06
    机型
    -0.06
    #↵↵
    -0.06
    紀
    -0.06
    POSITIVE LOGITS
     cardi
    0.07
    .After
    0.07
     лит
    0.07
     wzgl
    0.07
     пара
    0.06
     Guar
    0.06
    ⟱
    0.06
     tion
    0.06
     lado
    0.06
    .isfile
    0.06
    Act Density 0.048%

    No Known Activations