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

    Neuronpedia

    INDEX
    Explanations

    +

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    remarks
    -0.08
    anten
    -0.07
     ##
    -0.07
    ье
    -0.07
    .findByIdAndUpdate
    -0.07
    At
    -0.07
     updatedAt
    -0.07
     completo
    -0.07
    (interp
    -0.06
    ModelProperty
    -0.06
    POSITIVE LOGITS
     Javier
    0.07
    metrics
    0.06
    director
    0.06
     injust
    0.06
     thrift
    0.06
     perme
    0.06
     clicks
    0.06
    輯
    0.06
     bound
    0.06
    КТ
    0.06
    Act Density 0.031%

    No Known Activations