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

    Neuronpedia

    INDEX
    Explanations

    Suffixes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     manipulation
    -0.07
    ียบ
    -0.07
     fps
    -0.07
    avings
    -0.06
    _duration
    -0.06
    knowledge
    -0.06
     Bengals
    -0.06
     Sensor
    -0.06
    وح
    -0.06
    amente
    -0.06
    POSITIVE LOGITS
     Clash
    0.07
    (tab
    0.06
     iht
    0.06
     biên
    0.06
    �
    0.06
     البحر
    0.06
     Ping
    0.06
    popover
    0.06
     Thank
    0.06
     통
    0.06
    Act Density 0.123%

    No Known Activations