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

    Neuronpedia

    INDEX
    Explanations

    AI Chatbot and not a professional

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     trif
    0.89
     ton
    0.84
     no
    0.80
     sugar
    0.79
     spect
    0.76
     nest
    0.75
     lease
    0.75
     rent
    0.73
     seat
    0.73
     ins
    0.71
    POSITIVE LOGITS
     hilfre
    1.02
    MSFont
    0.95
    staben
    0.94
    ResponseMessage
    0.92
     compromet
    0.90
    œuvre
    0.87
     شرطونه
    0.87
    Criminal
    0.87
     Bestellung
    0.86
    ponenten
    0.85
    Act Density 0.006%

    No Known Activations