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

    Neuronpedia

    INDEX
    Explanations

    Department

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     deploy
    0.52
    륨
    0.49
     फैक्टर
    0.48
    deploy
    0.48
     पार्टनर
    0.47
     платфор
    0.46
     shark
    0.45
     परसेंट
    0.45
     dep
    0.44
     niektó
    0.44
    POSITIVE LOGITS
     departments
    0.49
     excused
    0.45
     विभागा
    0.45
    ித்த
    0.45
    ственный
    0.44
    ana
    0.44
    departments
    0.43
     budget
    0.42
    alities
    0.42
    ustion
    0.41
    Act Density 0.006%

    No Known Activations