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

    Neuronpedia

    INDEX
    Explanations

    Ember

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Thế
    -0.07
    <|start_header_id|>
    -0.07
    355
    -0.06
    396
    -0.06
     qui
    -0.06
     растение
    -0.06
     Aydın
    -0.06
    ethylene
    -0.06
     UserInfo
    -0.06
     toy
    -0.06
    POSITIVE LOGITS
     Ember
    0.08
     موب
    0.08
    ABEL
    0.07
     heck
    0.07
     matters
    0.07
    ember
    0.07
    orable
    0.07
    ーブル
    0.07
    BER
    0.07
    -bars
    0.07
    Act Density 0.001%

    No Known Activations