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

    Neuronpedia

    INDEX
    Explanations

    configuration settings

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Second
    -0.07
    家喻户
    -0.07
    converted
    -0.07
    (('
    -0.07
    ḇ
    -0.06
    ((&
    -0.06
    CUS
    -0.06
    Iran
    -0.06
    蓐
    -0.06
    Gamma
    -0.06
    POSITIVE LOGITS
    外语
    0.07
     meny
    0.07
     exchanged
    0.07
    단체
    0.07
     dermat
    0.07
    между
    0.06
     kości
    0.06
    ご紹
    0.06
    Href
    0.06
     GetString
    0.06
    Act Density 0.040%

    No Known Activations