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

    Neuronpedia

    INDEX
    Explanations

    listing examples

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ila
    -0.07
     وأ
    -0.07
    �
    -0.07
    養
    -0.07
    /con
    -0.07
     fö
    -0.07
     всю
    -0.07
     ventana
    -0.07
    谷爱
    -0.07
    landı
    -0.07
    POSITIVE LOGITS
    竞争对手
    0.08
    >());↵↵
    0.07
    心意
    0.07
    ()
↵
↵
    0.07
     impartial
    0.07
    眼皮
    0.06
     grading
    0.06
    .part
    0.06
    经营者
    0.06
     braking
    0.06
    Act Density 0.007%

    No Known Activations