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

    Neuronpedia

    INDEX
    Explanations

    productivity and to-do lists

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	graph
    -0.08
    ège
    -0.07
     Healing
    -0.07
    ление
    -0.06
    .Alignment
    -0.06
    甚至还
    -0.06
     EDUC
    -0.06
    _stack
    -0.06
    ACTION
    -0.06
    /constants
    -0.06
    POSITIVE LOGITS
    Strip
    0.07
     Дм
    0.07
     slid
    0.07
    }})↵
    0.07
    娆
    0.07
     qs
    0.07
    游览
    0.07
     Yugosl
    0.06
     :::
    0.06
     }
↵
    0.06
    Act Density 0.035%

    No Known Activations