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

    Neuronpedia

    INDEX
    Explanations

    fun activities and places

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    http
    0.61
     venerable
    0.59
     numai
    0.57
     prudent
    0.56
        
    0.56
    ..............
    0.54
     parochial
    0.54
     .
    0.53
     http
    0.53
     descriptive
    0.53
    POSITIVE LOGITS
    🫶
    1.09
     tiktok
    1.04
    🥹
    0.97
     increíble
    0.95
     idk
    0.94
    🫧
    0.93
     photoshoot
    0.91
     TikTok
    0.89
     🥰
    0.89
    🥺
    0.88
    Act Density 0.003%

    No Known Activations