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

    Neuronpedia

    INDEX
    Explanations

    important

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     dosage
    -0.07
     �
    -0.06
    autoreleasepool
    -0.06
    κυ
    -0.06
    内部
    -0.06
    erty
    -0.06
     retry
    -0.06
    uft
    -0.06
     GOODS
    -0.06
    帮
    -0.06
    POSITIVE LOGITS
    (Display
    0.06
     مهم
    0.06
     Chronicle
    0.06
     McL
    0.06
    Ў
    0.06
    г
    0.06
    ُم
    0.06
     раст
    0.06
    Generator
    0.06
     hairs
    0.06
    Act Density 0.030%

    No Known Activations