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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     SMS
    -0.07
    jee
    -0.07
     sms
    -0.07
    Pref
    -0.06
     Gut
    -0.06
    аты
    -0.06
     Abrams
    -0.06
     Spor
    -0.06
     Beg
    -0.06
     Purdue
    -0.06
    POSITIVE LOGITS
     accident
    0.07
    长度
    0.07
    [unit
    0.07
    ....
    0.06
    ダイ
    0.06
    INIT
    0.06
    _ACK
    0.06
    oubted
    0.06
     DEFINE
    0.06
    _topology
    0.06
    Act Density 0.363%

    No Known Activations