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

    Neuronpedia

    INDEX
    Explanations

    support groups

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .PNG
    -0.06
    Authors
    -0.06
    .cr
    -0.06
    (space
    -0.06
    ทร
    -0.06
     truy
    -0.06
     WN
    -0.06
    .phone
    -0.06
    .TH
    -0.06
    @brief
    -0.06
    POSITIVE LOGITS
    디시
    0.07
     cic
    0.07
    tran
    0.07
    esis
    0.07
    isks
    0.06
     [...
    0.06
     humour
    0.06
     stationed
    0.06
    receipt
    0.06
    -access
    0.06
    Act Density 0.059%

    No Known Activations