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

    Neuronpedia

    INDEX
    Explanations

    Sentiment

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     specialization
    -0.07
    !");↵
    -0.06
     experiencing
    -0.06
     Edwin
    -0.06
     Gives
    -0.06
    ных
    -0.06
    (&
    -0.06
    ="(
    -0.06
    esco
    -0.06
    ticks
    -0.06
    POSITIVE LOGITS
     �
    0.07
    createQuery
    0.07
    PRIVATE
    0.07
     Breitbart
    0.07
     immoral
    0.07
     بازی
    0.06
     GameManager
    0.06
    IKE
    0.06
    ,L
    0.06
    似的
    0.06
    Act Density 0.023%

    No Known Activations