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

    Neuronpedia

    INDEX
    Explanations

    National Suicide Prevention Lifeline

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     warrants
    0.91
     disorder
    0.74
     ware
    0.72
     editions
    0.71
     assisting
    0.70
     warrant
    0.69
     committees
    0.69
     thin
    0.68
     wrestling
    0.67
     disorders
    0.66
    POSITIVE LOGITS
    TikTok
    1.05
    Drone
    0.93
    गंगा
    0.87
    Quran
    0.86
     Metaverse
    0.85
    Biden
    0.84
     ర
    0.83
    Payload
    0.83
    Pyrazole
    0.83
    Lora
    0.83
    Act Density 0.017%

    No Known Activations