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

    Neuronpedia

    INDEX
    Explanations

    carry

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    �
    -0.06
     compartments
    -0.06
    .animation
    -0.06
     depend
    -0.06
     EntityType
    -0.06
    işti
    -0.06
    _skills
    -0.06
     uvád
    -0.06
     lái
    -0.06
    teen
    -0.06
    POSITIVE LOGITS
     weddings
    0.06
    appoint
    0.06
     Alice
    0.06
    式
    0.06
     sugars
    0.06
    Rick
    0.06
    Retail
    0.06
    lara
    0.06
     monoc
    0.06
     differential
    0.06
    Act Density 0.011%

    No Known Activations