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

    Neuronpedia

    INDEX
    Explanations

    multiplications

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     causes
    -0.08
     remedies
    -0.07
     causas
    -0.07
    京
    -0.07
     ubuntu
    -0.07
    incip
    -0.07
     observing
    -0.07
    adies
    -0.07
     responders
    -0.07
    ୟ
    -0.07
    POSITIVE LOGITS
     costly
    0.10
     expensive
    0.10
     Needed
    0.10
     تكلفة
    0.09
     затрат
    0.09
    一次
    0.09
    次数
    0.09
     операции
    0.09
     toán
    0.09
     notwendigen
    0.09
    Act Density 0.008%

    No Known Activations