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

    Neuronpedia

    INDEX
    Explanations

    code delimiters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    சிக்கும்
    0.81
    ิร์
    0.75
    ैग
    0.74
    賁
    0.71
     ($\
    0.70
     genitori
    0.69
     تے
    0.69
     বাংলাদেশকে
    0.66
     नगर
    0.65
    활
    0.64
    POSITIVE LOGITS
     ”
    1.93
     “
    1.92
     “.
    1.91
     “[
    1.89
     “‘
    1.88
     "..
    1.87
    「
    1.86
     “…
    1.82
     """
    1.82
     “(
    1.81
    Act Density 0.066%

    No Known Activations