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

    Neuronpedia

    INDEX
    Explanations

    Inability/negation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    真是
    -0.07
    遺
    -0.07
     若要
    -0.07
     Whatsapp
    -0.07
    怪
    -0.07
    }','
    -0.06
     tud
    -0.06
     vurgu
    -0.06
    (ad
    -0.06
     нужно
    -0.06
    POSITIVE LOGITS
    ricks
    0.07
    っち
    0.06
    u
    0.06
    allocate
    0.06
     Ashe
    0.06
    έρα
    0.06
    bserv
    0.06
    λογία
    0.06
     PyQt
    0.06
    advert
    0.06
    Act Density 0.195%

    No Known Activations