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

    Neuronpedia

    INDEX
    Explanations

    listing conjunctions and nouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Education
    0.91
    ழிப்பு
    0.82
    க்தி
    0.79
     jeweil
    0.78
    ன்மை
    0.78
     பொருள்
    0.76
    மானம்
    0.75
    Strength
    0.74
     बेटी
    0.73
    Grace
    0.72
    POSITIVE LOGITS
     gadgets
    1.72
     sculptures
    1.67
     resolutions
    1.64
     entrees
    1.64
     routers
    1.64
     viruses
    1.64
     folders
    1.62
     conditioners
    1.62
     songs
    1.61
     amplifiers
    1.61
    Act Density 1.135%

    No Known Activations