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

    Neuronpedia

    INDEX
    Explanations

    public keys

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    突破
    -0.08
     juggling
    -0.07
     governed
    -0.07
     regiment
    -0.07
    avior
    -0.07
    提醒
    -0.07
    otis
    -0.07
     revived
    -0.07
     backstage
    -0.07
     rhyme
    -0.07
    POSITIVE LOGITS
     pública
    0.11
     públic
    0.11
    公開
    0.10
    公开
    0.10
     publicly
    0.10
     공개
    0.10
     publique
    0.10
     publi
    0.10
     públicas
    0.09
    (public
    0.09
    Act Density 0.004%

    No Known Activations