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

    Neuronpedia

    INDEX
    Explanations

    scientific papers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    柔軟
    0.42
     zonder
    0.42
    诸
    0.40
     medicines
    0.39
    不想
    0.39
    諸
    0.39
     discrepancies
    0.38
     cuadrados
    0.38
     لا
    0.38
     incarnation
    0.38
    POSITIVE LOGITS
     पारिवार
    0.47
     Validate
    0.41
     বিস্ফ
    0.39
    olutely
    0.39
    family
    0.38
    WindowEvent
    0.38
     doubtless
    0.38
    پيديا
    0.37
    шат
    0.37
     poten
    0.37
    Act Density 0.000%

    No Known Activations