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

    Neuronpedia

    INDEX
    Explanations

    .

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    テー
    0.54
    爀
    0.53
     শার
    0.52
     আকর্ষণ
    0.52
    蔺
    0.51
     СССР
    0.50
    ｽ
    0.50
    턱
    0.50
    irus
    0.50
     लं
    0.50
    POSITIVE LOGITS
     joh
    0.67
    vand
    0.60
     reasonably
    0.59
    巡
    0.59
     john
    0.58
     Brix
    0.58
     vand
    0.57
     reasonable
    0.56
     Vad
    0.56
     Giov
    0.55
    Act Density 0.002%

    No Known Activations