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

    Neuronpedia

    INDEX
    Explanations

    conditional phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     urbana
    0.46
     pertenec
    0.45
     urbano
    0.45
     industriel
    0.45
     berasal
    0.44
     generell
    0.44
     gesellschaft
    0.43
     vuos
    0.43
     intellectuals
    0.42
     tradiz
    0.42
    POSITIVE LOGITS
    Якщо
    0.51
    Pokud
    0.47
    Jeśli
    0.45
    Чтобы
    0.44
    Nếu
    0.44
    Hvis
    0.42
    יל
    0.42
    ฟ
    0.42
    不僅
    0.42
    ник
    0.42
    Act Density 0.071%

    No Known Activations