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

    Neuronpedia

    INDEX
    Explanations

    reb

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    闲置
    -0.08
    >>↵
    -0.07
     lifespan
    -0.07
    ilan
    -0.07
    但它
    -0.07
    ROLL
    -0.07
    飲
    -0.07
    楮
    -0.07
     универ
    -0.07
    	style
    -0.07
    POSITIVE LOGITS
     reb
    0.08
    _bool
    0.08
     mia
    0.07
    (head
    0.07
    /products
    0.07
     хорошо
    0.06
     mothers
    0.06
    дет
    0.06
     subsequ
    0.06
    _epoch
    0.06
    Act Density 0.005%

    No Known Activations