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
     initialise
    -0.07
    Mods
    -0.07
     AppState
    -0.07
    噔
    -0.07
     لتح
    -0.06
    モデル
    -0.06
    .AddItem
    -0.06
    nodeName
    -0.06
     שנת
    -0.06
    awesome
    -0.06
    POSITIVE LOGITS
    ↵
    0.10
     :↵
    0.09
    ↵
    0.09
    :↵
    0.09
    )
↵
    0.09
    }.↵
    0.08
    ,
    0.08
    ;↵
    0.08
     ...↵
    0.08
    ....↵
    0.08
    Act Density 2.549%

    No Known Activations