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

    Neuronpedia

    INDEX
    Explanations

    bilateral relations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     phiên
    -0.07
    \Controller
    -0.07
    撅
    -0.07
    空
    -0.06
     הזכ
    -0.06
     U
    -0.06
     rud
    -0.06
    strlen
    -0.06
    Amazon
    -0.06
    to
    -0.06
    POSITIVE LOGITS
    ~~~~
    0.07
    如果是
    0.07
    يعة
    0.07
    .',
    0.07
    _items
    0.07
    IZATION
    0.06
    ית
    0.06
    orum
    0.06
    semblies
    0.06
    わけで
    0.06
    Act Density 0.038%

    No Known Activations