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

    Neuronpedia

    INDEX
    Explanations

    fund

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     produk
    -0.07
     flow
    -0.07
    ﱢ
    -0.06
     pared
    -0.06
     Railroad
    -0.06
     proceeds
    -0.06
     וכך
    -0.06
    нце
    -0.06
    뛔
    -0.06
    ʌ
    -0.06
    POSITIVE LOGITS
    委屈
    0.08
    分为
    0.07
     Blaze
    0.07
     Maintain
    0.07
    。。。
    0.07
    .Length
    0.07
     Trait
    0.07
    LED
    0.07
    ًا
    0.07
    wild
    0.07
    Act Density 0.020%

    No Known Activations