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

    Neuronpedia

    INDEX
    Explanations

    code incrementing and counting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    棻
    0.58
    荭
    0.55
    滏
    0.54
    珹
    0.54
    畞
    0.54
     vardır
    0.54
    这本书
    0.53
     Arzneim
    0.53
    豳
    0.53
    糇
    0.52
    POSITIVE LOGITS
    la
    0.58
     approval
    0.55
     grabs
    0.50
     sheet
    0.50
    approval
    0.48
    quarter
    0.48
    size
    0.46
    ROW
    0.46
    mybatis
    0.46
    tyw
    0.46
    Act Density 0.061%

    No Known Activations