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

    Neuronpedia

    INDEX
    Explanations

    multilingual concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     예를
    0.39
     heals
    0.38
     Example
    0.37
    OLE
    0.37
     sharp
    0.36
     SOLUTION
    0.35
    Example
    0.35
     reproduces
    0.34
     writeFile
    0.34
     rač
    0.34
    POSITIVE LOGITS
     ڈیز
    0.43
     ATLAS
    0.40
     perspectivas
    0.39
     seguridad
    0.39
     விவர
    0.39
    肓
    0.39
     fonti
    0.39
     documenti
    0.39
     leyenda
    0.39
     وقلنا
    0.39
    Act Density 0.000%

    No Known Activations