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

    Neuronpedia

    INDEX
    Explanations

    a

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ッツ
    -0.07
    лекс
    -0.07
    иль
    -0.07
     Wick
    -0.07
     Siege
    -0.07
    iversity
    -0.07
     FileUtils
    -0.06
    _BUCKET
    -0.06
     Lambda
    -0.06
    _opts
    -0.06
    POSITIVE LOGITS
    :{
↵
    0.06
     Authors
    0.06
    #aa
    0.06
     �
    0.06
     lắp
    0.06
     kurz
    0.06
    (foo
    0.06
     gear
    0.06
     trả
    0.06
     oneself
    0.06
    Act Density 0.023%

    No Known Activations