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

    Neuronpedia

    INDEX
    Explanations

    Platform

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .checkBox
    -0.07
    獲得
    -0.07
    _compare
    -0.07
    gle
    -0.06
    �
    -0.06
    ileri
    -0.06
    �
    -0.06
    cmd
    -0.06
     Kurul
    -0.06
    坚
    -0.06
    POSITIVE LOGITS
     watched
    0.07
    Steve
    0.06
     Micro
    0.06
     dolphins
    0.06
    Phone
    0.06
     Brad
    0.06
     Drake
    0.06
     micro
    0.06
     Dorm
    0.06
     cooler
    0.06
    Act Density 0.001%

    No Known Activations