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

    Neuronpedia

    INDEX
    Explanations

    Conversational blog-like text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Boundary
    -0.07
    コ
    -0.06
    _ref
    -0.06
    Shape
    -0.06
    (Calendar
    -0.06
     صند
    -0.06
    ('(
    -0.06
    plat
    -0.06
    Rows
    -0.06
    waves
    -0.06
    POSITIVE LOGITS
     Filtering
    0.07
    _salt
    0.07
     علي
    0.07
     ipad
    0.06
     offspring
    0.06
    getPage
    0.06
     محافظ
    0.06
     /////
    0.06
     uneasy
    0.06
    let
    0.06
    Act Density 0.052%

    No Known Activations