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

    Neuronpedia

    INDEX
    Explanations

    odd numbers and identifiers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    aqueous
    0.29
    physiological
    0.28
    embryon
    0.26
    Pourquoi
    0.25
    irradiated
    0.25
    queous
    0.25
    UnderWater
    0.25
    痱
    0.25
    Roasted
    0.25
    Lycodon
    0.25
    POSITIVE LOGITS
    _
    0.40
     values
    0.30
     companies
    0.30
    ↵
    0.28
     country
    0.27
     data
    0.27
     customers
    0.27
     time
    0.26
     plans
    0.26
     payments
    0.26
    Act Density 1.824%

    No Known Activations