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

    Neuronpedia

    INDEX
    Explanations

    (

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Yên
    -0.07
    𝘛
    -0.07
    iterated
    -0.07
     expertise
    -0.07
     Eğ
    -0.07
    iki
    -0.06
     Đó
    -0.06
    _ENDPOINT
    -0.06
     Religious
    -0.06
    ᵔ
    -0.06
    POSITIVE LOGITS
    Father
    0.08
    �ん
    0.07
    DEX
    0.07
    oad
    0.07
    RODUCTION
    0.07
     slower
    0.07
    StdString
    0.07
    _tag
    0.07
    Sha
    0.07
    emsp
    0.07
    Act Density 0.012%

    No Known Activations