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

    Neuronpedia

    INDEX
    Explanations

    importante

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Annotations
    -0.06
    (an
    -0.06
     beasts
    -0.06
     lg
    -0.06
    _original
    -0.06
    you
    -0.06
    orest
    -0.06
    _eg
    -0.06
    licts
    -0.06
     were
    -0.06
    POSITIVE LOGITS
     importante
    0.08
    /nav
    0.06
     forState
    0.06
     اهم
    0.06
    realDonaldTrump
    0.06
    #else
    0.06
     '<%=
    0.06
    .utc
    0.06
     좋
    0.06
     damning
    0.06
    Act Density 0.016%

    No Known Activations