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

    Neuronpedia

    INDEX
    Explanations

    "Subject" or "Dear"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    </i>
    0.40
    ：
    0.40
    ويس
    0.38
    </b>
    0.38
    ...)
    0.36
     )
    0.35
    ٩
    0.35
    observations
    0.34
     والر
    0.34
    络
    0.34
    POSITIVE LOGITS
    <h5>
    0.61
    ত
    0.57
    𝘁
    0.56
    an
    0.55
    a
    0.55
    ptăm
    0.54
    inaria
    0.52
    𝗮
    0.52
    𝒂
    0.51
    anbul
    0.51
    Act Density 0.002%

    No Known Activations