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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    <head
    -0.07
    ',{
    -0.06
     名無しさん
    -0.06
    teachers
    -0.06
    columnName
    -0.06
     Magnet
    -0.06
    疆
    -0.06
     Кра
    -0.06
     konusu
    -0.06
    (Print
    -0.06
    POSITIVE LOGITS
    achs
    0.07
     жил
    0.06
     soğ
    0.06
    -doc
    0.06
     urine
    0.06
     působ
    0.06
    anz
    0.06
     meine
    0.06
    REAM
    0.06
     tidak
    0.06
    Act Density 0.000%

    No Known Activations