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

    Neuronpedia

    INDEX
    Explanations

    Parentheses

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     consequence
    -0.08
    .todo
    -0.07
     TIMES
    -0.07
    Ď
    -0.07
    荪
    -0.07
    看电影
    -0.07
     Eck
    -0.06
     Wholesale
    -0.06
    对付
    -0.06
    帥
    -0.06
    POSITIVE LOGITS
    assert
    0.07
    Ｇ
    0.07
     Ya
    0.07
    Ground
    0.06
    Ops
    0.06
    0.06
    DB
    0.06
    center
    0.06
    ➥
    0.06
    &)
    0.06
    Act Density 0.031%

    No Known Activations