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

    Neuronpedia

    INDEX
    Explanations

    0

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    цька
    -0.63
    bihi
    -0.61
    mergeFrom
    -0.57
    ˈ
    -0.57
     Milling
    -0.55
     seconded
    -0.55
     Hunt
    -0.54
    ссию
    -0.54
    listdir
    -0.54
     Versailles
    -0.54
    POSITIVE LOGITS
     surla
    0.62
    AndroidJUnit
    0.52
     ích
    0.50
    rungsseite
    0.44
     mauvaises
    0.43
    円で
    0.41
    neſs
    0.40
    duras
    0.39
    PYX
    0.39
    polated
    0.38
    Act Density 0.004%

    No Known Activations