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

    Neuronpedia

    INDEX
    Explanations

    titanium

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     elem
    -0.07
    postal
    -0.07
    谢
    -0.07
     Narrow
    -0.07
     foregoing
    -0.07
     nội
    -0.07
     cardinal
    -0.07
    追い
    -0.07
    圃
    -0.07
     judicial
    -0.07
    POSITIVE LOGITS
    ᐈ
    0.08
     أمس
    0.08
    qué
    0.08
    💾
    0.07
    🌦
    0.07
    انا
    0.07
     synthetic
    0.07
    (Chat
    0.07
    𝘌
    0.07
    鹲
    0.07
    Act Density 0.011%

    No Known Activations