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

    Neuronpedia

    INDEX
    Explanations

    on

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     foster
    -0.07
    みなさん
    -0.07
    (password
    -0.07
     '/'↵
    -0.07
    精选
    -0.07
    查看更多
    -0.07
     Tabs
    -0.07
    VISION
    -0.07
     optimistic
    -0.07
    ('')↵
    -0.07
    POSITIVE LOGITS
    Lua
    0.08
    <dyn
    0.07
    אולם
    0.07
    داول
    0.07
    phon
    0.07
    يب
    0.06
    工艺
    0.06
     роли
    0.06
    rei
    0.06
     Dro
    0.06
    Act Density 0.004%

    No Known Activations