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

    Neuronpedia

    INDEX
    Explanations

    image/accentuate certain

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     поведения
    0.50
    मण
    0.47
     ши
    0.46
    丢失
    0.44
     marchand
    0.43
     નીચે
    0.42
    다가
    0.42
    нием
    0.42
     worrisome
    0.41
     פרו
    0.41
    POSITIVE LOGITS
     Autodesk
    0.49
     Tutto
    0.47
     Clean
    0.46
     Latex
    0.44
     Unity
    0.44
    Clean
    0.44
     Remix
    0.43
     absolument
    0.42
    ک
    0.42
     Anything
    0.42
    Act Density 0.036%

    No Known Activations