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

    Neuronpedia

    INDEX
    Explanations

    strang

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     laundry
    -0.06
     dv
    -0.06
     tên
    -0.06
     servings
    -0.06
     dataTable
    -0.06
     lect
    -0.06
     Cue
    -0.06
     electromagnetic
    -0.06
     tent
    -0.06
    Reporting
    -0.06
    POSITIVE LOGITS
     Stocks
    0.07
     withheld
    0.06
    .RESULT
    0.06
     Степ
    0.06
     same
    0.06
     exem
    0.06
    .preventDefault
    0.06
    ữa
    0.06
    ้องการ
    0.06
     ΑΓ
    0.06
    Act Density 0.001%

    No Known Activations