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

    Neuronpedia

    INDEX
    Explanations

    unwanted sexual

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    }$.
    0.46
    。『
    0.45
    nYou
    0.42
     gating
    0.41
    <unused51>
    0.41
    。《
    0.41
     égard
    0.41
     CREATE
    0.40
    。<
    0.40
    there
    0.40
    POSITIVE LOGITS
     carbs
    0.44
     ramen
    0.44
     moisturizer
    0.43
     selfies
    0.42
     commute
    0.42
     allergies
    0.41
     Tinder
    0.41
     diet
    0.41
    喜欢的
    0.40
     pizza
    0.40
    Act Density 0.069%

    No Known Activations