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

    Neuronpedia

    INDEX
    Explanations

    question parts or numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ren
    0.71
    ществ
    0.69
    it
    0.68
     क्रोध
    0.66
    ar
    0.66
    n
    0.65
    You
    0.65
    Company
    0.64
    rantes
    0.64
    sixth
    0.64
    POSITIVE LOGITS
     antibiotic
    0.74
     thoroughly
    0.67
     microbial
    0.67
     freely
    0.66
     Neutron
    0.66
     adaptive
    0.64
     fluoro
    0.64
     extensively
    0.63
     systematically
    0.62
     উহা
    0.61
    Act Density 0.036%

    No Known Activations