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

    Neuronpedia

    INDEX
    Explanations

    especially during cycle

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     hacker
    0.33
     Roboto
    0.33
     Comput
    0.33
    计算机
    0.33
     geek
    0.33
     comput
    0.32
     Hadoop
    0.32
     QuickBooks
    0.32
     computer
    0.32
     (
    0.31
    POSITIVE LOGITS
    arrerol
    0.37
    restrial
    0.36
    +](=
    0.35
    qualiter
    0.34
    同様
    0.33
     नमी
    0.33
    pubescens
    0.32
    similar
    0.31
    untungan
    0.31
    ąpi
    0.31
    Act Density 0.142%

    No Known Activations