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

    Neuronpedia

    INDEX
    Explanations

    comma

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     oft
    -0.08
     |↵
    -0.07
    Plus
    -0.07
    ({});↵
    -0.07
    �
    -0.07
     overhaul
    -0.07
     wear
    -0.07
    -plus
    -0.07
    ाशी
    -0.07
    unis
    -0.07
    POSITIVE LOGITS
     consecutive
    0.09
     തമ്മ
    0.08
     যাচ্ছে
    0.08
    erz
    0.08
     IRead
    0.08
     Ending
    0.08
     spaced
    0.08
     estaria
    0.08
    ક્રમ
    0.08
     leerling
    0.08
    Act Density 0.028%

    No Known Activations