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

    Neuronpedia

    INDEX
    Explanations

    technical terms

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    0.63
    并购
    0.61
    依次
    0.61
    ப்பட்ட
    0.59
    ниями
    0.57
     అవ
    0.56
     زم
    0.56
    關鍵
    0.56
    潴
    0.56
    immen
    0.55
    POSITIVE LOGITS
     MOS
    0.61
    cps
    0.60
    MOS
    0.59
     Held
    0.58
     हर्ष
    0.57
     split
    0.57
    rated
    0.57
    soft
    0.56
    ohid
    0.56
     vl
    0.56
    Act Density 0.000%

    No Known Activations