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

    Neuronpedia

    INDEX
    Explanations

    (

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Badge
    -0.07
    رياضي
    -0.07
    凭借
    -0.07
    .Student
    -0.07
    旗舰
    -0.07
    ☖
    -0.07
    円
    -0.07
    你应该
    -0.07
     disadvantaged
    -0.07
    Decoration
    -0.07
    POSITIVE LOGITS
     ℝ
    0.08
    wart
    0.08
    纂
    0.07
    _mix
    0.07
    �
    0.07
    ór
    0.07
     certainty
    0.07
     informant
    0.07
     exports
    0.07
     Narr
    0.06
    Act Density 0.002%

    No Known Activations