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

    Neuronpedia

    INDEX
    Explanations

    qap after me

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     manicure
    0.88
     skateboarding
    0.86
     hairstyles
    0.83
     diğer
    0.81
     pedicure
    0.81
     সম্পূর্ণরূপে
    0.80
     polyvinyl
    0.80
     ఇతర
    0.79
     trigonometric
    0.79
     corticoster
    0.79
    POSITIVE LOGITS
     Philly
    0.85
     Row
    0.80
     Friend
    0.78
     W
    0.73
     Specs
    0.73
    R
    0.72
     Plus
    0.71
     Dots
    0.70
    Q
    0.70
    X
    0.70
    Act Density 0.582%

    No Known Activations