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

    Neuronpedia

    INDEX
    Explanations

    Numbers and percentage

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    可怕
    -0.07
    /connection
    -0.07
     Form
    -0.07
     bleed
    -0.07
    .related
    -0.06
    /logs
    -0.06
    别
    -0.06
    栈
    -0.06
    תז
    -0.06
    (logger
    -0.06
    POSITIVE LOGITS
    Ｕ
    0.07
    ивать
    0.07
     })
    0.07
    	jQuery
    0.07
     wurde
    0.07
    >)
    0.07
     devices
    0.06
    رين
    0.06
    Currency
    0.06
    ).↵
    0.06
    Act Density 0.052%

    No Known Activations