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

    Neuronpedia

    INDEX
    Explanations

    text snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    �
    -0.06
     witches
    -0.06
     encontrado
    -0.06
     Intellectual
    -0.06
    .combine
    -0.06
     textual
    -0.06
     tant
    -0.06
     Rank
    -0.06
    屋
    -0.06
     qualche
    -0.06
    POSITIVE LOGITS
     предостав
    0.07
     Werk
    0.07
    ()})↵
    0.06
    şı
    0.06
    �
    0.06
    gh
    0.06
    ذ
    0.06
    rounded
    0.06
    zee
    0.06
    λε
    0.06
    Act Density 0.001%

    No Known Activations