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

    Neuronpedia

    INDEX
    Explanations

    website section titles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    inescence
    0.40
     rø
    0.39
     листопада
    0.39
     uniqueness
    0.38
    čnost
    0.37
    }~
    0.37
    恬
    0.37
     glory
    0.37
     omission
    0.37
    जीवी
    0.36
    POSITIVE LOGITS
    Related
    0.67
     Related
    0.66
    Similar
    0.60
     RELATED
    0.60
    Trending
    0.59
    related
    0.58
    Frequently
    0.57
     Similar
    0.56
    Popular
    0.55
     popular
    0.54
    Act Density 0.000%

    No Known Activations