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

    Neuronpedia

    INDEX
    Explanations

    asiento

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     mese
    0.54
     other
    0.51
     Außerdem
    0.51
     olabilir
    0.48
     または
    0.48
     olie
    0.47
     sugiere
    0.47
    posable
    0.47
     funktioniert
    0.46
     verwenden
    0.45
    POSITIVE LOGITS
     roared
    0.63
    不已
    0.61
    般的
    0.61
     galore
    0.59
     furiously
    0.59
     দুর্দান্ত
    0.59
     നിറഞ്ഞ
    0.58
     ensue
    0.57
    🔥🔥
    0.57
    しながら
    0.56
    Act Density 0.000%

    No Known Activations