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

    Neuronpedia

    INDEX
    Explanations

    organizational behavior and education

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Recommended
    0.43
     constellations
    0.38
    ⋮
    0.37
    ignan
    0.37
     উৎপ
    0.37
    ستخدم
    0.37
     Nodes
    0.37
     রূপান্তরিত
    0.36
     Nodo
    0.36
    hookrightarrow
    0.35
    POSITIVE LOGITS
     pareil
    0.47
     frontal
    0.41
    attacks
    0.41
     whipped
    0.40
     gravely
    0.40
    homework
    0.38
     Sq
    0.38
     eure
    0.38
     brutal
    0.37
     folk
    0.37
    Act Density 0.000%

    No Known Activations