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

    Neuronpedia

    INDEX
    Explanations

    signature acknowledging

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     butyl
    0.46
    (
    0.43
     articulating
    0.43
    出典
    0.42
     indicate
    0.42
    Regressor
    0.41
     roofing
    0.40
     facilement
    0.40
     popupButton
    0.40
     দিকের
    0.40
    POSITIVE LOGITS
    t
    0.46
    fff
    0.46
    vil
    0.44
    ol
    0.44
     Healthcare
    0.44
     Hospitality
    0.44
    naph
    0.44
     Sustainability
    0.43
    เนิน
    0.43
    acr
    0.43
    Act Density 0.005%

    No Known Activations