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

    Neuronpedia

    INDEX
    Explanations

    peace of mind

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    讓他們
    -0.10
     problem
    -0.08
    刷
    -0.07
     zostać
    -0.07
    해주
    -0.07
     indicate
    -0.07
    使其
    -0.07
    也没什么
    -0.07
     consisted
    -0.06
     OVERRIDE
    -0.06
    POSITIVE LOGITS
     Bewert
    0.08
    HOLDER
    0.08
    olars
    0.07
    جيد
    0.07
    operation
    0.07
    рег
    0.07
    resizing
    0.07
    ⏪
    0.07
     Rahman
    0.07
    -san
    0.07
    Act Density 0.046%

    No Known Activations