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

    Neuronpedia

    INDEX
    Explanations

    code and queries

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     wallpapers
    -0.07
     contradictory
    -0.07
     světě
    -0.06
     Something
    -0.06
     ______
    -0.06
     �
    -0.06
     Quản
    -0.06
    -même
    -0.06
    ウィ
    -0.06
    iy
    -0.06
    POSITIVE LOGITS
     Typeface
    0.08
    _this
    0.07
     \
↵
    0.06
    }↵
    0.06
    ----------↵
    0.06
    _checker
    0.06
    pper
    0.06
     commenced
    0.06
     Perr
    0.06
    recommended
    0.06
    Act Density 0.000%

    No Known Activations