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

    Neuronpedia

    INDEX
    Explanations

    beyond breath

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     universo
    0.50
     popolo
    0.48
     dimas
    0.47
     negocios
    0.47
     elenc
    0.46
     clase
    0.45
     persamaan
    0.45
     listas
    0.45
     touring
    0.45
     bruta
    0.45
    POSITIVE LOGITS
    ৫
    0.44
    ędz
    0.43
    ï
    0.41
    ånd
    0.40
    ewnętr
    0.40
     дает
    0.40
    ٥
    0.40
     và
    0.39
    ন্ত্রণ
    0.39
     має
    0.39
    Act Density 0.003%

    No Known Activations