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

    Neuronpedia

    INDEX
    Explanations

    blog posts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Phoenix
    -0.08
    ♱
    -0.07
     mystery
    -0.07
     GAM
    -0.07
     lodge
    -0.07
    党和政府
    -0.07
     premise
    -0.07
     элект
    -0.07
     vice
    -0.07
     BIND
    -0.07
    POSITIVE LOGITS
    练习
    0.07
    𝕒
    0.07
    ße
    0.07
     ePub
    0.07
    𬴃
    0.07
     DHCP
    0.06
     VER
    0.06
    痹
    0.06
    ordination
    0.06
    新开传奇
    0.06
    Act Density 0.014%

    No Known Activations