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

    Neuronpedia

    INDEX
    Explanations

    cancer

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Hãy
    -0.07
     군
    -0.07
     prices
    -0.06
     Allowed
    -0.06
    位置
    -0.06
     emphasize
    -0.06
     Kern
    -0.06
     Minneapolis
    -0.06
    .temperature
    -0.06
     示例
    -0.06
    POSITIVE LOGITS
    elite
    0.07
    .LoadScene
    0.06
    ibur
    0.06
    ريل
    0.06
    _PRED
    0.06
    omit
    0.06
    kor
    0.06
     pur
    0.06
     �
    0.06
     Κο
    0.06
    Act Density 0.004%

    No Known Activations