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

    Neuronpedia

    INDEX
    Explanations

    creating jobs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ویل
    -0.07
    Badge
    -0.07
    ''.
    -0.06
     convincing
    -0.06
    ۸
    -0.06
    No
    -0.06
    请
    -0.06
    �
    -0.06
    _models
    -0.06
    Urls
    -0.06
    POSITIVE LOGITS
     Mate
    0.07
    (surface
    0.07
     ;;=
    0.07
     illegally
    0.06
     ра�
    0.06
     MÜ
    0.06
    ριν
    0.06
    :user
    0.06
    _SCROLL
    0.06
     Foley
    0.06
    Act Density 0.067%

    No Known Activations