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

    Neuronpedia

    INDEX
    Explanations

    byte

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    否
    -0.07
    regex
    -0.07
     Tells
    -0.07
     allergy
    -0.07
    첧
    -0.06
    ‛
    -0.06
    /hooks
    -0.06
     indigenous
    -0.06
    ủ
    -0.06
    .cfg
    -0.06
    POSITIVE LOGITS
    哪怕
    0.07
     MacOS
    0.07
    &r
    0.07
    🎨
    0.07
    ⚑
    0.06
    📧
    0.06
    ruitment
    0.06
    %";↵
    0.06
    嚄
    0.06
    비용
    0.06
    Act Density 0.007%

    No Known Activations