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

    Neuronpedia

    INDEX
    Explanations

    differ

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    nické
    -0.07
    interop
    -0.07
    نت
    -0.07
    َا
    -0.07
    ente
    -0.07
    ón
    -0.07
     capability
    -0.06
    (change
    -0.06
    永
    -0.06
     accidents
    -0.06
    POSITIVE LOGITS
     differ
    0.15
     differed
    0.15
     differs
    0.14
     differing
    0.09
    iffer
    0.09
    ByText
    0.07
    .REG
    0.06
    .Fprintf
    0.06
     Dagger
    0.06
    ific
    0.06
    Act Density 0.007%

    No Known Activations