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

    Neuronpedia

    INDEX
    Explanations

    Abstracts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Cruise
    -0.06
     thereof
    -0.06
    mits
    -0.06
     Arena
    -0.06
     dara
    -0.06
    _nome
    -0.06
    elts
    -0.06
     Spreadsheet
    -0.06
    ieber
    -0.06
     Thesis
    -0.06
    POSITIVE LOGITS
    (play
    0.08
    是我
    0.07
     climbed
    0.07
     отлич
    0.07
    	handle
    0.07
    (send
    0.07
    biz
    0.06
    .inc
    0.06
    ">(
    0.06
     geral
    0.06
    Act Density 0.002%

    No Known Activations