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

    Neuronpedia

    INDEX
    Explanations

    code examples

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     বর্তমানে
    -0.09
    기사
    -0.08
     earthquakes
    -0.08
    (CC
    -0.08
     referencias
    -0.08
    ARTICLE
    -0.08
     telescope
    -0.08
     hillside
    -0.07
     optimise
    -0.07
     other's
    -0.07
    POSITIVE LOGITS
     Porter
    0.08
     Mol
    0.08
     Milan
    0.08
     Silva
    0.08
    nale
    0.08
     Porto
    0.07
     Иван
    0.07
    �
    0.07
    illac
    0.07
    <|endoftext|>
    0.07
    Act Density 0.041%

    No Known Activations