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

    Neuronpedia

    INDEX
    Explanations

    things that vary

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     eğer
    0.40
     তখনই
    0.35
    可能的
    0.35
    そらく
    0.34
     বৃহত্তর
    0.34
    繕
    0.34
     conceivably
    0.33
    ǹ
    0.33
    제를
    0.33
     κόσ
    0.33
    POSITIVE LOGITS
     vary
    2.28
     varies
    2.27
    vary
    1.77
     Vary
    1.66
     varía
    1.63
     varia
    1.62
     variar
    1.58
     differs
    1.55
     varying
    1.48
     varier
    1.44
    Act Density 0.019%

    No Known Activations