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

    Neuronpedia

    INDEX
    Explanations

    complex words and concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    …)
    0.42
    PayPal
    0.40
    英语
    0.38
    ...)
    0.38
    _),
    0.38
    Polit
    0.37
    Geplaatst
    0.37
     पीपल
    0.37
    Facebook
    0.36
    rapes
    0.36
    POSITIVE LOGITS
     sara
    0.35
     लें
    0.32
     sä
    0.32
     rin
    0.31
    нь
    0.30
     cfg
    0.30
     intersect
    0.30
    </h3>
    0.30
     inspect
    0.30
     hå
    0.30
    Act Density 0.000%

    No Known Activations