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

    Neuronpedia

    INDEX
    Explanations

    try to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     terhadap
    0.63
     anos
    0.63
     destacar
    0.59
     humana
    0.58
     bilayer
    0.58
    }.
    0.57
     manus
    0.57
     parameter
    0.57
     .
    0.57
     samba
    0.56
    POSITIVE LOGITS
     ಲಿ
    0.64
    ור
    0.61
    ৭
    0.58
     جوړونکی
    0.57
    то
    0.57
    esz
    0.55
    нику
    0.54
    나
    0.54
    ৫৫
    0.54
    আবার
    0.53
    Act Density 0.047%

    No Known Activations