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

    Neuronpedia

    INDEX
    Explanations

    Code snippets

    np_max-act · gemini-2.0-flash

    This neuron responds to pandas row-selection expressions (e.g. boolean masks inside `.loc`/`.iloc`), i.e. code patterns used to filter or index DataFrame rows.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     малень
    -0.07
    /includes
    -0.07
    的时候
    -0.07
     актив
    -0.06
     BlackBerry
    -0.06
    озв
    -0.06
     featured
    -0.06
    education
    -0.06
    اير
    -0.06
     fox
    -0.06
    POSITIVE LOGITS
     Carb
    0.06
     Kosovo
    0.06
     악
    0.06
    SuppressWarnings
    0.06
     masturb
    0.06
    @SuppressWarnings
    0.06
     %=
    0.06
     Wesley
    0.06
     Tomato
    0.06
     �
    0.06
    Act Density 0.063%

    No Known Activations