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

    Neuronpedia

    INDEX
    Explanations

    background

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     peace
    -0.07
     rx
    -0.07
     ice
    -0.06
     inclusive
    -0.06
    indows
    -0.06
     safer
    -0.06
     içindeki
    -0.06
    (red
    -0.06
     thư
    -0.06
    .publish
    -0.06
    POSITIVE LOGITS
     backgrounds
    0.09
     background
    0.08
     handicap
    0.07
     upbringing
    0.07
     pathways
    0.06
     Prelude
    0.06
    途
    0.06
    디시
    0.06
    148
    0.06
     doPost
    0.06
    Act Density 0.010%

    No Known Activations