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

    Neuronpedia

    INDEX
    Explanations

    micro

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Ed
    -0.07
    .St
    -0.07
    菩提
    -0.07
    otor
    -0.07
     offerings
    -0.07
     cham
    -0.07
    合适
    -0.07
     resp
    -0.07
    .edu
    -0.07
    <?=$
    -0.07
    POSITIVE LOGITS
    웝
    0.08
    꺾
    0.08
    สงคร
    0.07
     progressBar
    0.07
    ImageRelation
    0.07
    .discount
    0.07
    딫
    0.07
    듄
    0.07
    رعا
    0.06
    ()){
    0.06
    Act Density 0.053%

    No Known Activations