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

    Neuronpedia

    INDEX
    Explanations

    physical forms or structures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     scrape
    0.48
     Oekra
    0.46
     wonderful
    0.45
     unexpectedly
    0.43
     「
    0.43
     pseud
    0.43
     appreciated
    0.42
    不足
    0.42
     gist
    0.42
     [];
    0.42
    POSITIVE LOGITS
    al
    0.59
    iu
    0.52
    upon
    0.47
    ua
    0.46
    års
    0.46
    rene
    0.46
    alog
    0.46
     नेक्स्ट
    0.45
    vány
    0.45
    ies
    0.44
    Act Density 0.000%

    No Known Activations