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

    Neuronpedia

    INDEX
    Explanations

    a

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    contract
    -0.07
    Alternate
    -0.06
    _tuples
    -0.06
    вок
    -0.06
    ầng
    -0.06
    erialization
    -0.06
    _rectangle
    -0.06
    �
    -0.06
     funding
    -0.06
    ]),
    -0.06
    POSITIVE LOGITS
     FIND
    0.07
     beforeEach
    0.07
     ud
    0.07
     (--
    0.06
    ocking
    0.06
    自分の
    0.06
     système
    0.06
    265
    0.06
     Spe
    0.06
     NAND
    0.06
    Act Density 0.035%

    No Known Activations