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

    Neuronpedia

    INDEX
    Explanations

    job and online tools

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    rated
    -0.07
     کلاس
    -0.07
    پر
    -0.06
    衛
    -0.06
    fried
    -0.06
     conformity
    -0.06
     lime
    -0.06
    وقت
    -0.06
     Gods
    -0.06
     naken
    -0.06
    POSITIVE LOGITS
     $__
    0.07
     something
    0.07
    .News
    0.06
    (exception
    0.06
    Auth
    0.06
     protobuf
    0.06
    ION
    0.06
    /table
    0.06
     Poll
    0.06
    Spy
    0.06
    Act Density 0.001%

    No Known Activations