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

    Neuronpedia

    INDEX
    Explanations

    we

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Derek
    -0.07
    h
    -0.07
    ave
    -0.07
    ?>&
    -0.06
    update
    -0.06
    _without
    -0.06
    重点
    -0.06
    AVE
    -0.06
    controller
    -0.06
     Raj
    -0.06
    POSITIVE LOGITS
    طي
    0.07
     našich
    0.07
    ään
    0.06
    상담
    0.06
    _gem
    0.06
    @pytest
    0.06
    wives
    0.06
     toggle
    0.06
     MÜ
    0.06
    τε
    0.06
    Act Density 0.049%

    No Known Activations