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

    Neuronpedia

    INDEX
    Explanations

    ((

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     doubly
    -0.06
    /******/
    -0.06
    ΟΦ
    -0.06
    ン�
    -0.06
    <Void
    -0.06
    Span
    -0.06
    _Label
    -0.06
    cerr
    -0.06
    (asset
    -0.06
     Mana
    -0.06
    POSITIVE LOGITS
     되는
    0.07
    /^
    0.07
     generated
    0.07
     renovations
    0.07
    fall
    0.07
     towering
    0.07
     afforded
    0.07
     autre
    0.06
     lobbyists
    0.06
     ousted
    0.06
    Act Density 0.001%

    No Known Activations