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

    Neuronpedia

    INDEX
    Explanations

    Stop words and punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    every
    -0.09
     Couldn't
    -0.08
    can't
    -0.08
     game's
    -0.08
     délicieux
    -0.08
     exorbit
    -0.08
     blindly
    -0.08
     shouldn't
    -0.08
    mites
    -0.08
    sins
    -0.08
    POSITIVE LOGITS
     reportedly
    0.13
    。据
    0.13
    主要
    0.10
    <|endoftext|>
    0.10
    ，截至
    0.09
     당시
    0.09
    。截至
    0.09
     notable
    0.09
    特点
    0.09
     상당
    0.09
    Act Density 0.198%

    No Known Activations