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

    Neuronpedia

    INDEX
    Explanations

    format

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    írk
    -0.07
     *[
    -0.07
    /im
    -0.06
    Dr
    -0.06
     ho
    -0.06
     exhaustive
    -0.06
    so
    -0.06
     convergence
    -0.06
    社
    -0.06
     ub
    -0.06
    POSITIVE LOGITS
     FILE
    0.07
     hindsight
    0.06
     Advent
    0.06
     кажд
    0.06
     Mock
    0.06
    XmlAttribute
    0.06
    score
    0.06
     đón
    0.06
    ервые
    0.06
    hcp
    0.06
    Act Density 0.019%

    No Known Activations