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

    Neuronpedia

    INDEX
    Explanations

    hypothesis

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    電
    -0.07
     livro
    -0.07
     cca
    -0.06
    ccd
    -0.06
     نور
    -0.06
     alanda
    -0.06
     trades
    -0.06
     Capac
    -0.06
     Wan
    -0.06
    literal
    -0.06
    POSITIVE LOGITS
     ([]
    0.07
     Dys
    0.07
    Noise
    0.06
     HIP
    0.06
    Increased
    0.06
     krev
    0.06
    _CLOCK
    0.06
     borderRadius
    0.06
    ΟΦ
    0.06
    ByPrimaryKey
    0.06
    Act Density 0.002%

    No Known Activations