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

    Neuronpedia

    INDEX
    Explanations

    GNU General Public License

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ות
    2.75
    aków
    2.33
    tség
    2.11
    the
    2.08
    pc
    2.06
    table
    1.98
    苣
    1.94
    tik
    1.93
    t
    1.93
    it
    1.91
    POSITIVE LOGITS
    на
    2.53
    깐
    2.23
    ר
    2.06
    ज
    2.05
    ल
    2.03
    而且
    1.96
     appellees
    1.82
    রকম
    1.77
    ন
    1.75
    €™
    1.74
    Act Density 0.052%

    No Known Activations