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

    Neuronpedia

    INDEX
    Explanations

    model offering suggestions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Hooks
    0.75
    當然
    0.67
    वस
    0.66
    Actually
    0.66
    nada
    0.66
    Buzz
    0.65
     दरअसल
    0.65
     Tailwind
    0.65
    ంటే
    0.65
    buzz
    0.64
    POSITIVE LOGITS
     दीक्षित
    0.77
     traitement
    0.76
     bringen
    0.72
     pubescence
    0.71
    新的
    0.71
     لديك
    0.70
     daarna
    0.68
     possible
    0.68
     aussi
    0.68
     이제
    0.68
    Act Density 0.046%

    No Known Activations