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

    Neuronpedia

    INDEX
    Explanations

    requesting specific, brief descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    further
    0.42
     مزید
    0.41
     sequestration
    0.40
     further
    0.40
     další
    0.40
     дальнейшем
    0.40
     további
    0.38
     verder
    0.38
     dals
    0.38
    脛
    0.38
    POSITIVE LOGITS
     describe
    0.85
     description
    0.84
     möglichst
    0.84
     concisely
    0.84
     Describe
    0.83
    描述
    0.80
    Describe
    0.80
    尽可能
    0.80
    尽量
    0.80
     brief
    0.79
    Act Density 0.095%

    No Known Activations