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

    Neuronpedia

    INDEX
    Explanations

    based

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     dioxide
    -0.08
    issions
    -0.08
    index
    -0.07
    פח
    -0.07
    (y
    -0.07
    _comm
    -0.07
    分区
    -0.07
    𐭉
    -0.07
    �
    -0.07
     initiation
    -0.06
    POSITIVE LOGITS
     based
    0.10
    -based
    0.08
     the
    0.07
    datasets
    0.07
     Avatar
    0.07
    rote
    0.07
    �
    0.06
     Ram
    0.06
     มา
    0.06
    才行
    0.06
    Act Density 0.068%

    No Known Activations