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

    Neuronpedia

    INDEX
    Explanations

    time of day

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    每个人都
    -0.07
    ".$_
    -0.07
    (Encoding
    -0.06
     truyện
    -0.06
     kindness
    -0.06
     struggled
    -0.06
    Howard
    -0.06
    앐
    -0.06
    ▀
    -0.06
     urlpatterns
    -0.06
    POSITIVE LOGITS
    تقي
    0.08
    _AES
    0.08
     ACL
    0.07
     conclus
    0.07
     block
    0.07
    _leave
    0.07
     Vest
    0.07
    ㈳
    0.07
    .qml
    0.07
     Particip
    0.07
    Act Density 0.051%

    No Known Activations