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

    Neuronpedia

    INDEX
    Explanations

    Business/company contexts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Claud
    -0.07
     Feld
    -0.07
    brates
    -0.06
     Pf
    -0.06
    ʵ
    -0.06
    ennen
    -0.06
     Киев
    -0.06
    (dev
    -0.06
    enerate
    -0.06
    镢
    -0.06
    POSITIVE LOGITS
    allenges
    0.07
    "url
    0.06
    .Parameters
    0.06
    采访时
    0.06
     }>↵
    0.06
    ኤ
    0.06
    >())↵
    0.06
     accesses
    0.06
    _purchase
    0.06
    修建
    0.06
    Act Density 0.046%

    No Known Activations