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

    Neuronpedia

    INDEX
    Explanations

    closer to reality

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     realice
    0.46
    Pharmacy
    0.41
     pharmacy
    0.41
    ♀
    0.40
     virulent
    0.39
     wst
    0.39
     नरेंद्र
    0.39
    ティア
    0.39
    Tier
    0.38
    TypeValue
    0.38
    POSITIVE LOGITS
    ui
    0.43
     Moll
    0.38
     Puff
    0.38
    𝘂
    0.37
    উট
    0.37
     Full
    0.36
    Partial
    0.36
     flannel
    0.36
     Encounter
    0.36
    UI
    0.36
    Act Density 0.000%

    No Known Activations