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
    _constants
    -0.07
    ชน
    -0.07
     resisted
    -0.07
     nuances
    -0.07
     hates
    -0.07
     initialise
    -0.07
    ToolTip
    -0.06
    莫过于
    -0.06
    This
    -0.06
     animator
    -0.06
    POSITIVE LOGITS
    鬶
    0.08
    赶来
    0.08
    疲惫
    0.07
    >f
    0.07
    ,f
    0.06
    刚才
    0.06
    的妻子
    0.06
    _moves
    0.06
     breat
    0.06
    🚶
    0.06
    Act Density 0.003%

    No Known Activations