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

    Neuronpedia

    INDEX
    Explanations

    ays

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	src
    -0.07
    .Shape
    -0.06
    一个人
    -0.06
     Veranst
    -0.06
    .initial
    -0.06
     jud
    -0.06
    енсив
    -0.06
    	raise
    -0.06
    顺
    -0.06
    Sorted
    -0.06
    POSITIVE LOGITS
    CTIONS
    0.07
    BD
    0.07
    tarı
    0.07
    985
    0.07
    ίσω
    0.06
    rought
    0.06
    vertime
    0.06
    ديد
    0.06
    .available
    0.06
     drafted
    0.06
    Act Density 0.003%

    No Known Activations