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

    Neuronpedia

    INDEX
    Explanations

    Biographical entries

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Cupertino
    -0.06
    /include
    -0.06
     Webster
    -0.06
     meilleurs
    -0.06
    ρέ
    -0.06
    …but
    -0.06
    iez
    -0.06
    .win
    -0.06
    íte
    -0.06
     실시
    -0.06
    POSITIVE LOGITS
     кры
    0.07
     augment
    0.06
    ATIONS
    0.06
    خب
    0.06
     aff
    0.06
     equiv
    0.06
     označ
    0.06
    '))↵
    0.06
    (ws
    0.06
     excerpt
    0.06
    Act Density 0.008%

    No Known Activations