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

    Neuronpedia

    INDEX
    Explanations

    Conjunctions, transition words

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Descriptions
    -0.07
     ｌ
    -0.07
    utom
    -0.06
    ----------------------------------------------------------------------------
    -0.06
    674
    -0.06
    .authentication
    -0.06
    ned
    -0.06
    _asset
    -0.06
    nge
    -0.06
     ヽ
    -0.06
    POSITIVE LOGITS
     buys
    0.07
     polic
    0.06
    ै.
    0.06
     Аль
    0.06
     Transcript
    0.06
    ैं.
    0.06
    /INFO
    0.06
    营
    0.06
    си
    0.06
     куп
    0.06
    Act Density 0.069%

    No Known Activations