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

    Neuronpedia

    INDEX
    Explanations

    letter

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ُو
    -0.08
    dda
    -0.06
    SHOW
    -0.06
    モ
    -0.06
    оты
    -0.06
    وجد
    -0.06
    стра
    -0.06
     Zen
    -0.06
     deadliest
    -0.06
    َ
    -0.06
    POSITIVE LOGITS
    ']:↵
    0.08
    (term
    0.07
    "]],↵
    0.07
     curve
    0.07
    ).↵
    0.07
    :
↵
↵
    0.07
    ']):↵
    0.07
    (date
    0.07
     TRANSACTION
    0.07
    	logging
    0.06
    Act Density 0.002%

    No Known Activations