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

    Neuronpedia

    INDEX
    Explanations

    Scientific/medical papers

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    agine
    -0.07
    ovice
    -0.07
    аран
    -0.06
    nak
    -0.06
    ін
    -0.06
     데
    -0.06
    ARGE
    -0.06
     }
↵
↵
↵
↵
    -0.06
     질문
    -0.06
     protobuf
    -0.06
    POSITIVE LOGITS
    .parseColor
    0.06
     sass
    0.06
    .getResource
    0.06
     ním
    0.06
    issippi
    0.06
     NSLog
    0.06
     καθ
    0.06
     console
    0.06
     Nha
    0.06
     trest
    0.06
    Act Density 0.123%

    No Known Activations