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

    Neuronpedia

    INDEX
    Explanations

    can be

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ising
    0.62
    '"
    0.55
    array
    0.55
    ्राट
    0.55
    ashing
    0.55
     lanjutkan
    0.53
    र्जा
    0.53
    rin
    0.52
     gelungen
    0.52
    राज्य
    0.52
    POSITIVE LOGITS
    ামুটি
    0.52
    ю
    0.50
    ש
    0.50
    ем
    0.50
    ন
    0.50
    િ
    0.47
    ك
    0.47
    леты
    0.45
     Surprisingly
    0.45
    ાર્થ
    0.45
    Act Density 0.363%

    No Known Activations