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

    Neuronpedia

    INDEX
    Explanations

    coding terms

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     বাসিন্দা
    0.64
     지하
    0.62
    кологи
    0.61
    izhou
    0.61
     프리
    0.60
     ቦ
    0.59
    anoic
    0.59
    cosis
    0.58
     זי
    0.57
    سط
    0.57
    POSITIVE LOGITS
     heng
    0.73
     hen
    0.65
    你想
    0.63
     herman
    0.63
     heer
    0.63
    延续
    0.62
    prend
    0.60
     rach
    0.60
     deur
    0.59
     heir
    0.59
    Act Density 0.000%

    No Known Activations