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

    Neuronpedia

    INDEX
    Explanations

    ulated

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     realiz
    -0.07
     tér
    -0.07
    TING
    -0.06
    errat
    -0.06
    metry
    -0.06
     tertiary
    -0.06
    belie
    -0.06
     mass
    -0.06
     told
    -0.06
     sacrifice
    -0.06
    POSITIVE LOGITS
    <\/
    0.08
    .dt
    0.06
    .execute
    0.06
    _temperature
    0.06
    >(),↵
    0.06
    collapse
    0.06
    ।↵
    0.06
    졌다
    0.06
     Cục
    0.06
    ++.
    0.06
    Act Density 0.000%

    No Known Activations