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

    Neuronpedia

    INDEX
    Explanations

    architecture/design

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -copy
    -0.07
    选择
    -0.07
    '%
    -0.06
     Signing
    -0.06
     DPS
    -0.06
    >e
    -0.06
    livě
    -0.06
    جو
    -0.06
    /web
    -0.06
    DON
    -0.06
    POSITIVE LOGITS
     -*-
    0.06
     صاد
    0.06
     komt
    0.06
     окруж
    0.06
    ULL
    0.06
    .qual
    0.06
    pray
    0.06
     fend
    0.06
     orada
    0.06
     Sage
    0.06
    Act Density 0.055%

    No Known Activations