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

    Neuronpedia

    INDEX
    Explanations

    varied text snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     kromě
    -0.08
     опера
    -0.06
     regained
    -0.06
    跡
    -0.06
     teens
    -0.06
     soundtrack
    -0.06
     commenced
    -0.06
    瀬
    -0.06
    Repo
    -0.06
     prefetch
    -0.06
    POSITIVE LOGITS
     geral
    0.07
     UEFA
    0.07
     блю
    0.07
    setParameter
    0.06
    ції
    0.06
     crus
    0.06
    ț
    0.06
    (o
    0.06
     assertTrue
    0.06
    ~-~-
    0.06
    Act Density 0.148%

    No Known Activations