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

    Neuronpedia

    INDEX
    Explanations

    Common words and punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ститут
    -0.07
    iesz
    -0.06
     realization
    -0.06
    rules
    -0.06
     meg
    -0.06
    ammu
    -0.06
     badge
    -0.06
    acobian
    -0.06
    inars
    -0.06
     prepared
    -0.06
    POSITIVE LOGITS
     Bergen
    0.06
    ินทร
    0.06
     Harden
    0.06
    obsolete
    0.06
    (DE
    0.06
     dehydration
    0.06
     نشده
    0.06
    黃
    0.06
     yyyy
    0.06
    _ONCE
    0.06
    Act Density 0.000%

    No Known Activations