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

    Neuronpedia

    INDEX
    Explanations

    applications

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    から
    -0.07
    issan
    -0.07
     Floral
    -0.06
    رانی
    -0.06
    بد
    -0.06
    =''
    -0.06
    θεια
    -0.06
    尼
    -0.06
     voters
    -0.06
    ้ำ
    -0.06
    POSITIVE LOGITS
     depreci
    0.08
    Penn
    0.07
    ét
    0.06
     gr
    0.06
     altering
    0.06
     ।↵
    0.06
    [f
    0.06
     *@
    0.06
    [g
    0.06
    ственной
    0.06
    Act Density 0.131%

    No Known Activations