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

    Neuronpedia

    INDEX
    Explanations

    market

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    n
    0.74
    b
    0.72
    at
    0.66
    ról
    0.63
    ↵↵
    0.63
    l
    0.60
    ↵
    0.54
    c
    0.53
    bruk
    0.52
    ,
    0.52
    POSITIVE LOGITS
    0
    0.64
    This
    0.63
    し
    0.57
    ری
    0.56
    I
    0.52
    With
    0.52
    この
    0.52
     This
    0.51
    রামর্শ
    0.51
    این
    0.51
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.