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

    Neuronpedia

    INDEX
    Explanations

    academic concepts and proposals

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Go
    0.39
     tutorial
    0.39
    стика
    0.38
     tutorials
    0.38
    送到
    0.38
    Ka
    0.37
    Go
    0.37
    tutorial
    0.37
    Thompson
    0.37
    Neha
    0.37
    POSITIVE LOGITS
     đình
    0.43
     chyba
    0.40
     independently
    0.40
     ulc
    0.40
    =(-
    0.39
    機関
    0.39
     jobSearch
    0.39
     beerCount
    0.38
    ப்பே
    0.37
     clarifications
    0.37
    Act Density 0.000%

    No Known Activations