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

    Neuronpedia

    INDEX
    Explanations

    street addresses

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     inflatable
    -0.06
     NV
    -0.06
     查询
    -0.06
     atop
    -0.06
    bur
    -0.06
     найбільш
    -0.06
     unify
    -0.06
    '^
    -0.05
     Fair
    -0.05
    手机号
    -0.05
    POSITIVE LOGITS
     Barrett
    0.08
    ールド
    0.07
    elerinin
    0.07
    ，大
    0.07
    getCell
    0.06
     خون
    0.06
    _
↵
    0.06
    angu
    0.06
    straint
    0.06
    ็็
    0.06
    Act Density 0.001%

    No Known Activations