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

    Neuronpedia

    INDEX
    Explanations

    to be

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    فر
    -0.07
     rá
    -0.07
     چت
    -0.07
    pane
    -0.06
     інтерес
    -0.06
     Boca
    -0.06
    vertise
    -0.06
     hostages
    -0.06
    рал
    -0.06
    �
    -0.06
    POSITIVE LOGITS
     reconstructed
    0.07
     assigned
    0.07
    _del
    0.06
     inflate
    0.06
    )])↵
    0.06
     longing
    0.06
    Approved
    0.06
     predominant
    0.06
     electromagnetic
    0.06
    >;↵↵
    0.06
    Act Density 0.076%

    No Known Activations