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

    Neuronpedia

    INDEX
    Explanations

    section separators

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    un
    0.51
    ou
    0.50
    r
    0.49
    ны
    0.49
    ژن
    0.46
    ud
    0.46
    ğ
    0.46
    Референ
    0.45
    ün
    0.45
     Тем
    0.44
    POSITIVE LOGITS
     watering
    0.47
     frantic
    0.46
     modalities
    0.45
     दिव्या
    0.44
     diving
    0.42
     flavors
    0.42
     dives
    0.42
     casualties
    0.41
     WIS
    0.41
     Watering
    0.41
    Act Density 0.000%

    No Known Activations