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

    Neuronpedia

    INDEX
    Explanations

    #

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    :[↵
    -0.06
    杜
    -0.06
    (value
    -0.06
    '||
    -0.06
    版
    -0.06
     Wil
    -0.06
    -sign
    -0.06
     Destiny
    -0.06
    ቴ
    -0.06
    ny
    -0.06
    POSITIVE LOGITS
    enterprise
    0.08
     Loch
    0.07
    擊
    0.07
     Vuex
    0.07
    haft
    0.07
    aaS
    0.07
    ungi
    0.07
    orders
    0.07
     Quite
    0.07
    Across
    0.07
    Act Density 0.001%

    No Known Activations