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

    Neuronpedia

    INDEX
    Explanations

    lists about sequences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     $\
    0.47
    ă
    0.45
     \
    0.45
     \#
    0.40
    âh
    0.39
    …
    0.39
     concession
    0.38
    Â
    0.38
    </b>
    0.38
     Junction
    0.38
    POSITIVE LOGITS
    ेलकम
    0.53
     Pickett
    0.48
    ☜
    0.48
    ფილი
    0.46
    经典的
    0.46
    驭
    0.46
     behö
    0.45
     upd
    0.45
    োজনের
    0.45
    펭
    0.45
    Act Density 0.005%

    No Known Activations