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

    Neuronpedia

    INDEX
    Explanations

    code syntax and structure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    return
    0.69
    numero
    0.64
     количество
    0.60
     மேற்கொள்ள
    0.59
    количество
    0.58
    quantidade
    0.58
    coordinates
    0.58
    cantidad
    0.58
    mostrar
    0.57
    conditions
    0.57
    POSITIVE LOGITS
     glitches
    0.74
     melanin
    0.74
     robotic
    0.69
     lounging
    0.69
     keratin
    0.69
     lurking
    0.68
     smeared
    0.68
     tyrann
    0.68
     firsthand
    0.67
     PFAS
    0.66
    Act Density 0.177%

    No Known Activations