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

    Neuronpedia

    INDEX
    Explanations

    database connection parameters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    uslar
    0.39
    acja
    0.38
     approachable
    0.38
     Footh
    0.38
    ailand
    0.37
     Matters
    0.37
    ksz
    0.37
     Daya
    0.37
     instructors
    0.36
    ache
    0.36
    POSITIVE LOGITS
    Gly
    0.39
     Philadelphia
    0.39
    这家
    0.38
     Maguire
    0.38
     የአ
    0.38
     گیرد
    0.37
     glycine
    0.36
    XMLHttpRequest
    0.36
     аро
    0.36
     гли
    0.36
    Act Density 0.003%

    No Known Activations