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

    Neuronpedia

    INDEX
    Explanations

    door

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Hockey
    -0.07
     Tues
    -0.07
     succession
    -0.07
    Birth
    -0.06
     appe
    -0.06
     wartime
    -0.06
     saline
    -0.06
    ,the
    -0.06
    欢
    -0.06
     ulcer
    -0.06
    POSITIVE LOGITS
     thước
    0.06
    aniel
    0.06
    msgs
    0.06
    eof
    0.06
    ownload
    0.06
    μιουργ
    0.06
    charger
    0.06
     nord
    0.06
    ังน
    0.06
     redund
    0.06
    Act Density 0.033%

    No Known Activations