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

    Neuronpedia

    INDEX
    Explanations

    social media

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    gid
    -0.07
    research
    -0.07
    许多
    -0.06
    480
    -0.06
    魔
    -0.06
    <Car
    -0.06
    งของ
    -0.06
     scho
    -0.06
     daylight
    -0.06
    汽
    -0.06
    POSITIVE LOGITS
     QT
    0.06
    istrict
    0.06
     Failure
    0.06
     contempt
    0.06
     dün
    0.06
    ).'</
    0.06
     ´
    0.06
     Britt
    0.06
    wig
    0.06
    Promise
    0.06
    Act Density 0.011%

    No Known Activations