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

    Neuronpedia

    INDEX
    Explanations

    Names

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     sonra
    -0.07
     手
    -0.07
    流
    -0.07
     broadly
    -0.07
     xrange
    -0.06
    Parse
    -0.06
     List
    -0.06
     Object
    -0.06
     willing
    -0.06
    Spi
    -0.06
    POSITIVE LOGITS
    (numbers
    0.07
    _User
    0.06
    Iran
    0.06
    DRAM
    0.06
    (dec
    0.06
    ]string
    0.06
    ValueHandling
    0.06
     gamm
    0.06
    _ptrs
    0.06
    xBA
    0.06
    Act Density 0.003%

    No Known Activations