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

    Neuronpedia

    INDEX
    Explanations

    interest rate

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    不幸
    0.55
    $?
    0.53
    :
    0.52
     espe
    0.50
    яс
    0.50
    $
    0.50
    不安定
    0.47
    ：
    0.47
    不利
    0.46
    '
    0.45
    POSITIVE LOGITS
    ColorBit
    0.56
    BufOffset
    0.54
     makers
    0.53
    akers
    0.52
    IsDir
    0.52
    obuf
    0.51
    ⟣
    0.51
    em
    0.51
    ராம
    0.51
    SubDirectory
    0.51
    Act Density 0.001%

    No Known Activations