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

    Neuronpedia

    INDEX
    Explanations

    theories of relativity

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ار
    2.04
    abline
    1.93
    ため
    1.79
    ی
    1.71
    ੋ
    1.59
     ópt
    1.58
    ik
    1.57
    má
    1.52
    𝒌
    1.51
    aneous
    1.50
    POSITIVE LOGITS
     grandeur
    1.82
    hanging
    1.76
     resemblance
    1.73
    koop
    1.71
    पंथी
    1.71
    inprogress
    1.66
    verticalLayout
    1.65
    trombone
    1.64
     QVector
    1.64
    rubber
    1.62
    Act Density 0.029%

    No Known Activations