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

    Neuronpedia

    INDEX
    Explanations

    new

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    MESSAGE
    -0.07
    .management
    -0.07
    ौ
    -0.07
    оз
    -0.06
     всё
    -0.06
    مین
    -0.06
    Quest
    -0.06
     ně
    -0.06
     день
    -0.06
    oin
    -0.06
    POSITIVE LOGITS
    拿
    0.07
     Dow
    0.07
     benefici
    0.06
     versatile
    0.06
    持
    0.06
    Messenger
    0.06
    (u
    0.06
     Occasionally
    0.06
    essenger
    0.06
    =tf
    0.06
    Act Density 0.005%

    No Known Activations