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

    Neuronpedia

    INDEX
    Explanations

    do

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    有助
    -0.08
    ifting
    -0.07
     distracted
    -0.07
    (suffix
    -0.07
     cycling
    -0.07
     search
    -0.07
    会
    -0.07
     Still
    -0.07
    凭什么
    -0.07
     Util
    -0.07
    POSITIVE LOGITS
    (Object
    0.07
    يلة
    0.07
    (unit
    0.07
     adjacency
    0.06
    detail
    0.06
     nước
    0.06
     breadth
    0.06
    ظام
    0.06
    增值税
    0.06
     frontal
    0.06
    Act Density 0.001%

    No Known Activations