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

    Neuronpedia

    INDEX
    Explanations

    to be

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    кової
    -0.08
    ικο
    -0.07
     come
    -0.07
    (nd
    -0.06
     Helping
    -0.06
    (mp
    -0.06
     Norris
    -0.06
    's
    -0.06
     Scha
    -0.06
    lecture
    -0.06
    POSITIVE LOGITS
    "),↵↵
    0.07
    .url
    0.07
    。”↵↵
    0.06
    AIM
    0.06
    _:*
    0.06
    ，↵↵
    0.06
    pac
    0.06
    ”。↵↵
    0.06
    -present
    0.06
     Hib
    0.06
    Act Density 0.073%

    No Known Activations