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

    Neuronpedia

    INDEX
    Explanations

    publishing companies and university presses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Botox
    0.67
     formal
    0.64
     get
    0.63
     tool
    0.63
     personal
    0.63
     made
    0.62
    গায়
    0.60
     compound
    0.59
     gets
    0.58
     goggles
    0.58
    POSITIVE LOGITS
     Publishing
    1.94
     Publications
    1.86
     Publishers
    1.81
     publishers
    1.75
     publishing
    1.66
    publishing
    1.66
    Publish
    1.56
     publisher
    1.54
     Verlag
    1.53
     प्रकाशन
    1.53
    Act Density 0.006%

    No Known Activations