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
    .getRequest
    -0.07
     Lâm
    -0.07
    מוצא
    -0.07
    とはい
    -0.07
    bew
    -0.07
    ໃ
    -0.07
    中心城区
    -0.07
    توجيه
    -0.07
    .classList
    -0.07
     Ngọc
    -0.07
    POSITIVE LOGITS
     Marshal
    0.07
    𝕥
    0.07
     Stuttgart
    0.07
    utions
    0.06
    具
    0.06
     Really
    0.06
    彼ら
    0.06
     latch
    0.06
     abril
    0.06
     ≠
    0.06
    Act Density 0.001%

    No Known Activations