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

    Neuronpedia

    INDEX
    Explanations

    say "as I"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    韨
    -0.08
    昈
    -0.08
    🦙
    -0.08
    _vue
    -0.08
    🏮
    -0.07
    vecs
    -0.07
    /apt
    -0.07
    .maxcdn
    -0.07
    挺好
    -0.07
    后悔
    -0.07
    POSITIVE LOGITS
     Hav
    0.07
     receptors
    0.07
    -Th
    0.07
     data
    0.07
    生长
    0.07
    发起
    0.07
     EW
    0.07
     rais
    0.06
    宣
    0.06
    相对
    0.06
    Act Density 0.003%

    No Known Activations