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

    Neuronpedia

    INDEX
    Explanations

    protecting family, teacher

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     відповіда
    0.40
     подтвер
    0.38
     تص
    0.37
     Acting
    0.37
     Flav
    0.37
    Transicao
    0.36
     kontaktu
    0.36
     поэтому
    0.36
     присоеди
    0.35
     Жа
    0.35
    POSITIVE LOGITS
    早就
    0.41
    ul
    0.35
    าว
    0.35
    lll
    0.35
    ণ্ডল
    0.34
    imming
    0.34
     Sangh
    0.34
     stove
    0.33
    *)(
    0.33
    Indexed
    0.33
    Act Density 0.000%

    No Known Activations