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

    Neuronpedia

    INDEX
    Explanations

    ^

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    拥抱
    -0.07
    ratio
    -0.07
    达尔
    -0.07
    颓
    -0.07
     popped
    -0.07
    舍
    -0.07
    孓
    -0.07
    ��
    -0.07
    	boolean
    -0.06
    幻想
    -0.06
    POSITIVE LOGITS
    ]^
    0.08
     medida
    0.07
     qa
    0.07
     autoload
    0.07
     />}
    0.07
     كانوا
    0.07
    ∊
    0.07
    ivated
    0.07
     -/↵
    0.06
     onStop
    0.06
    Act Density 0.001%

    No Known Activations