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

    Neuronpedia

    INDEX
    Explanations

    Business mergers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _backward
    -0.07
    _phone
    -0.07
    notice
    -0.07
     salary
    -0.07
     -->↵
    -0.06
     Hate
    -0.06
     populous
    -0.06
    糖
    -0.06
    )[:
    -0.06
     ک
    -0.06
    POSITIVE LOGITS
     神马
    0.07
    ersistent
    0.06
     amalg
    0.06
    _POL
    0.06
    PL
    0.06
    _firstname
    0.06
    markers
    0.06
     DL
    0.06
    _tbl
    0.06
     separators
    0.06
    Act Density 0.431%

    No Known Activations