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

    Neuronpedia

    INDEX
    Explanations

    Scientific experiments

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ΩΤ
    -0.08
     sciences
    -0.07
     getopt
    -0.07
    -way
    -0.06
     склада
    -0.06
     JT
    -0.06
     کوت
    -0.06
     JP
    -0.06
     poetry
    -0.06
    -bo
    -0.06
    POSITIVE LOGITS
     演
    0.06
    іблі
    0.06
     Email
    0.06
    kili
    0.06
    _slug
    0.06
     현재
    0.06
    ουν
    0.06
     gef
    0.06
     Pornhub
    0.06
    tur
    0.06
    Act Density 0.028%

    No Known Activations