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

    Neuronpedia

    INDEX
    Explanations

    L'Hopital's rule

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     weet
    0.40
     number
    0.39
    number
    0.37
    贴
    0.36
     число
    0.36
     everything
    0.35
     numero
    0.35
     joie
    0.35
     წ
    0.35
     congested
    0.34
    POSITIVE LOGITS
    菈
    0.40
     Mour
    0.38
    ρού
    0.38
    ologici
    0.37
    iliz
    0.37
     Designed
    0.37
    izou
    0.36
    Outfit
    0.36
    ILY
    0.36
    ovirus
    0.36
    Act Density 0.000%

    No Known Activations