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

    Neuronpedia

    INDEX
    Explanations

    HTML tags and code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (tr
    -0.07
     buggy
    -0.07
    法律法规
    -0.07
    icago
    -0.07
    |array
    -0.07
     Anthony
    -0.07
    押
    -0.06
    ♱
    -0.06
    近两年
    -0.06
    Defined
    -0.06
    POSITIVE LOGITS
    撕
    0.07
     EQUI
    0.07
    廚
    0.07
    QUE
    0.07
    posite
    0.07
     sill
    0.07
    _FILE
    0.06
    anness
    0.06
     Chall
    0.06
    宓
    0.06
    Act Density 0.016%

    No Known Activations