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

    Neuronpedia

    INDEX
    Explanations

    Wow

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    改
    -0.07
     البي
    -0.07
    Root
    -0.07
    stalk
    -0.07
    lings
    -0.06
     Shore
    -0.06
     собира
    -0.06
     Erd
    -0.06
    ("|
    -0.06
     Abu
    -0.06
    POSITIVE LOGITS
     wow
    0.07
    Wow
    0.07
     Wow
    0.07
    _InternalArray
    0.07
    真是
    0.07
     victorious
    0.06
    .QLabel
    0.06
     slashes
    0.06
    wow
    0.06
    "])
    0.06
    Act Density 0.007%

    No Known Activations