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

    Neuronpedia

    INDEX
    Explanations

    evaluation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    <Player
    -0.07
     shore
    -0.07
     pump
    -0.06
     BigNumber
    -0.06
     suppress
    -0.06
     addresses
    -0.06
    шт
    -0.06
     suggest
    -0.06
    .SDK
    -0.06
     considers
    -0.06
    POSITIVE LOGITS
     Evaluation
    0.08
    ResponseType
    0.07
    resher
    0.07
    аніз
    0.07
    istinguished
    0.07
     foe
    0.07
     обязан
    0.07
    ैट
    0.07
     лет
    0.06
    elon
    0.06
    Act Density 0.012%

    No Known Activations