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

    Neuronpedia

    INDEX
    Explanations

    parts of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    мерикан
    0.40
    icel
    0.39
     amer
    0.38
    lcd
    0.37
     Ameri
    0.37
     responded
    0.37
     reacts
    0.36
    américa
    0.36
    amerikan
    0.35
     करीत
    0.35
    POSITIVE LOGITS
     pter
    0.44
     rama
    0.43
     Napoleon
    0.42
     Herzeg
    0.40
     rambling
    0.39
     Mughal
    0.39
     Magna
    0.39
     определения
    0.38
     reincarnation
    0.38
     Pto
    0.38
    Act Density 0.003%

    No Known Activations