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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Defensive
    -0.07
     konkrét
    -0.07
    .press
    -0.06
    _reserve
    -0.06
    .Expect
    -0.06
     make
    -0.06
     throw
    -0.06
     Lean
    -0.06
     Fraud
    -0.06
    Within
    -0.06
    POSITIVE LOGITS
     gameTime
    0.07
    copyright
    0.07
    ่น
    0.06
    _pose
    0.06
    .amazon
    0.06
    ındır
    0.06
    ोन
    0.06
    �
    0.06
     yytype
    0.06
     trademarks
    0.06
    Act Density 0.016%

    No Known Activations