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

    Neuronpedia

    INDEX
    Explanations

    sweater

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    מל
    -0.08
    (Collections
    -0.08
     pisc
    -0.07
    qv
    -0.07
    -routing
    -0.07
     подготов
    -0.07
     nome
    -0.07
    び
    -0.07
     jung
    -0.07
    Под
    -0.07
    POSITIVE LOGITS
    すれば
    0.08
    �
    0.08
    -tabs
    0.07
    ショップ
    0.07
    這樣的
    0.07
     особ
    0.07
     @@↵
    0.07
     sheet
    0.07
     repeated
    0.07
    weighted
    0.07
    Act Density 0.003%

    No Known Activations