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

    Neuronpedia

    INDEX
    Explanations

    Something from the past

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _working
    -0.07
    BuildContext
    -0.07
    𝕧
    -0.07
    =name
    -0.07
    的情形
    -0.07
    holds
    -0.07
    原因是
    -0.06
    [counter
    -0.06
    RIPTION
    -0.06
     проблем
    -0.06
    POSITIVE LOGITS
    โรงแรม
    0.07
     Artifact
    0.07
     căng
    0.07
    ><![
    0.07
    _Status
    0.07
     sa
    0.07
     tower
    0.07
    蕰
    0.07
    品味
    0.07
     revel
    0.06
    Act Density 0.059%

    No Known Activations