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

    Neuronpedia

    INDEX
    Explanations

    web addresses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     tried
    0.36
    記事
    0.36
     जोड़
    0.35
     Â
    0.35
    tried
    0.35
    égard
    0.35
     பிரச்ச
    0.34
     theyre
    0.34
    的一個
    0.34
     Verfü
    0.34
    POSITIVE LOGITS
    www
    0.59
     ftp
    0.52
     www
    0.47
    WWW
    0.47
    ftp
    0.45
    http
    0.42
    gic
    0.41
     http
    0.41
    venus
    0.41
    Publications
    0.40
    Act Density 0.002%

    No Known Activations