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

    Neuronpedia

    INDEX
    Explanations

    breakfast

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (describing
    -0.06
     hashlib
    -0.06
     prow
    -0.06
    ynchronized
    -0.06
    SharedPreferences
    -0.06
     협
    -0.06
     Fat
    -0.06
     Methodist
    -0.06
    불
    -0.06
    -Al
    -0.06
    POSITIVE LOGITS
    ));
↵
    0.06
     discour
    0.06
     milestone
    0.06
    età
    0.06
     Hobby
    0.06
     حسين
    0.06
    &B
    0.06
    .feedback
    0.06
    _panel
    0.06
    Phot
    0.05
    Act Density 0.003%

    No Known Activations